commit 5c940e6b6c3e9475ca9c94a8fb4b977e1f37fe42 Author: ModelHub XC Date: Sat Sep 26 20:04:29 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec032eb --- /dev/null +++ b/README.md @@ -0,0 +1,331 @@ +--- +license: apache-2.0 +language: +- en +- ja +base_model: +- llm-jp/llm-jp-4-32b-a3b-thinking +pipeline_tag: text-generation +library_name: transformers +--- + +# llm-jp-4-kappa-32b-a3b-v0.1 + +![kappa-images.003 (1)](https://cdn-uploads.huggingface.co/production/uploads/65f01b5235c5424c262c8be8/DjZxFJ3ic19pm4rkiHuOO.jpeg) + + +**llm-jp-4-kappa-32b-a3b-v0.1** は、**Third-intelligence** が研究開発の一環で試作した日本語・英語対応の Thinking 型大規模言語モデルです。[`llm-jp/llm-jp-4-32b-a3b-thinking`](https://huggingface.co/llm-jp/llm-jp-4-32b-a3b-thinking) をベースに、 + +- Reasoning(思考プロセスの生成)能力を強化するための **SFT (Supervised Fine-Tuning)** +- 数学・コード領域における **強化学習 (Reinforcement Learning)** +の 2 段階の追加学習を行い、ベースモデルが持つ日本語性能を維持しつつ、推論・数学・コーディング能力の向上を目指しました。 + +ベースモデルと同様、**Mixture-of-Experts (MoE) アーキテクチャ**(総パラメータ約 32B / activated 約 3B)を採用しているため、同規模の dense モデルと比較して推論時の計算コストを抑えつつ、高い性能を発揮します。 + +詳細については[技術ブログ](https://third-intelligence.com/ja/posts/kappa-v01-reasoning-post-training)を参照ください。 + +--- + +## モデル概要 + +| 項目 | 内容 | +|---|---| +| ベースモデル | [`llm-jp/llm-jp-4-32b-a3b-thinking`](https://huggingface.co/llm-jp/llm-jp-4-32b-a3b-thinking) | +| アーキテクチャ | Mixture-of-Experts (MoE), Thinking モデル | +| 総パラメータ数 | 約 32B | +| Activated パラメータ数 | 約 3B | +| 学習手法 | SFT(Reasoning 強化) + 強化学習(数学・コード) | +| 対応言語 | 日本語 / 英語 | +| 最大コンテキスト長 | 65,536 tokens | +| ライセンス | Apache License 2.0(ベースモデルの条件も継承) | + +--- + +## ベンチマーク + +評価には [swallow-llm/swallow-evaluation-instruct](https://github.com/swallow-llm/swallow-evaluation-instruct) を使用しました(OpenRouter 経由でモデルが使用できるよう、一部修正を加えました。) + +また、OpenRouter でデプロイされているモデルについては、serving しているプロバイダーの設定により量子化などが行われており、本来のフルプレシジョン版から性能が劣化している可能性があります。ただし、評価にあたっては OpenRouter 側の設定で可能な限り高いパフォーマンスとなるよう **Exacto** の設定を有効にしました。 + +LLM-as-a-judgeが必要になるベンチマークについては評価モデルにopenai/gpt-4.1を使用しました。(プロバイダーはAzureに固定しています。) + +### 比較対象モデル + +| 略称 | モデル ID | 備考 | +|---|---|---| +| **llm-jp-4-kappa (本モデル)** | `third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1` | 本モデル | +| llm-jp-4 | `llm-jp/llm-jp-4-32b-a3b-thinking` | ベースモデル | +| gpt-oss-20b | `openai/gpt-oss-20b` (via OpenRouter) | | +| nemotron-3-nano | `nvidia/nemotron-3-nano-30b-a3b` (via OpenRouter) | | +| qwen3-30b | `qwen/qwen3-30b-a3b-thinking-2507` (via OpenRouter) | | + + +### サマリー(主要スコア) + +> **太字** は各行の最高スコアを示します。 + +| ベンチマーク | **llm-jp-4-kappa (本モデル)** | llm-jp-4 | gpt-oss-20b | nemotron-3-nano | qwen3-30b | +|---|---:|---:|---:|---:|---:| +| MMLU ProX Japanese (avg) | 0.6724 | 0.6759 | 0.6886 | 0.5740 | **0.7547** | +| MMLU Pro English (avg) | 0.7025 | 0.6956 | 0.7343 | 0.7180 | **0.8038** | +| Japanese MT-Bench (avg) | **0.9339** | 0.9270 | 0.8749 | 0.8900 | 0.8693 | +| English MT-Bench (avg) | 0.9226 | 0.9220 | 0.8899 | 0.9216 | **0.9304** | +| JEMHopQA F1 | 0.6329 | **0.6391** | 0.4737 | 0.2329 | 0.5597 | +| MCLM Math 100 (Japanese) | 0.8788 | 0.8687 | 0.9394 | 0.8081 | **0.9697** | +| GPQA Diamond | 0.5505 | 0.4899 | 0.6364 | 0.5909 | **0.7121** | +| AIME 2024/2025 | 0.4333 | 0.3833 | 0.5667 | 0.3667 | **0.8833** | + +### Japanese MT-Bench(カテゴリ別) + +| カテゴリ | **llm-jp-4-kappa (本モデル)** | llm-jp-4 | gpt-oss-20b | nemotron-3-nano | qwen3-30b | +|---|---:|---:|---:|---:|---:| +| coding | **0.9480** | 0.9420 | 0.9340 | 0.9450 | 0.8680 | +| extraction | **0.8730** | 0.8650 | 0.8380 | 0.8030 | 0.8400 | +| humanities | **0.9870** | 0.9770 | 0.8300 | 0.9550 | 0.9540 | +| math | **0.9950** | 0.9800 | 0.9920 | 0.9070 | 0.9470 | +| reasoning | **0.8470** | 0.8310 | 0.8090 | 0.8050 | 0.7590 | +| roleplay | **0.9480** | 0.9340 | 0.8310 | 0.8720 | 0.8130 | +| stem | 0.9670 | **0.9770** | 0.9120 | 0.9610 | 0.9130 | +| writing | 0.9060 | **0.9100** | 0.8530 | 0.8720 | 0.8600 | +| 1st turn | **0.9545** | 0.9520 | 0.9145 | 0.8888 | 0.8930 | +| 2nd turn | **0.9133** | 0.9020 | 0.8353 | 0.8913 | 0.8455 | +| **平均** | **0.9339** | 0.9270 | 0.8749 | 0.8900 | 0.8693 | + +### English MT-Bench(カテゴリ別) + +| カテゴリ | **llm-jp-4-kappa (本モデル)** | llm-jp-4 | gpt-oss-20b | nemotron-3-nano | qwen3-30b | +|---|---:|---:|---:|---:|---:| +| coding | 0.9240 | **0.9340** | 0.9040 | 0.8910 | 0.8860 | +| extraction | 0.8590 | 0.8220 | 0.8610 | 0.8430 | **0.8980** | +| humanities | 0.9570 | **0.9800** | 0.9250 | 0.9410 | 0.9600 | +| math | 0.9990 | 0.9990 | 0.9720 | 0.9960 | **1.0000** | +| reasoning | 0.8460 | 0.8260 | 0.7590 | 0.8990 | **0.9030** | +| roleplay | 0.9290 | **0.9360** | 0.8710 | 0.9340 | 0.9090 | +| stem | **0.9910** | 0.9780 | 0.9380 | 0.9410 | 0.9730 | +| writing | 0.8760 | 0.9010 | 0.8890 | **0.9280** | 0.9140 | +| 1st turn | 0.9468 | 0.9368 | 0.9208 | **0.9523** | 0.9515 | +| 2nd turn | 0.8985 | 0.9073 | 0.8590 | 0.8910 | **0.9093** | +| **平均** | 0.9226 | 0.9220 | 0.8899 | 0.9216 | **0.9304** | + +### MMLU ProX Japanese / MMLU Pro English(科目別) + +
+📊 MMLU ProX Japanese 科目別スコアを開く + +| 科目 | **llm-jp-4-kappa (本モデル)** | llm-jp-4 | gpt-oss-20b | nemotron-3-nano | qwen3-30b | +|---|---:|---:|---:|---:|---:| +| business | 0.7338 | 0.7326 | 0.7782 | 0.5741 | **0.8238** | +| law | 0.3326 | 0.3472 | 0.3034 | 0.2899 | **0.4067** | +| psychology | 0.6454 | 0.6654 | 0.6654 | 0.5890 | **0.7180** | +| biology | 0.7950 | 0.7880 | 0.7964 | 0.6820 | **0.8522** | +| chemistry | 0.7686 | 0.7712 | 0.8012 | 0.6793 | **0.8640** | +| history | 0.5039 | 0.5223 | 0.5118 | 0.4173 | **0.5984** | +| other | 0.6006 | 0.5898 | 0.5931 | 0.5011 | **0.6656** | +| health | 0.6332 | 0.6332 | 0.6332 | 0.5109 | **0.6594** | +| economics | 0.7370 | 0.7322 | 0.7464 | 0.6351 | **0.8128** | +| math | 0.8586 | 0.8608 | 0.8993 | 0.7631 | **0.9023** | +| physics | 0.7929 | 0.7968 | 0.8075 | 0.6659 | **0.8676** | +| computer science | 0.7512 | 0.7537 | 0.8073 | 0.6634 | **0.8195** | +| philosophy | 0.5050 | 0.5170 | 0.5010 | 0.3928 | **0.5892** | +| engineering | 0.5160 | 0.5222 | 0.5470 | 0.4314 | **0.7379** | +| **平均** | 0.6724 | 0.6759 | 0.6886 | 0.5740 | **0.7547** | + +
+ +
+📊 MMLU Pro English 科目別スコアを開く + +| 科目 | **llm-jp-4-kappa (本モデル)** | llm-jp-4 | gpt-oss-20b | nemotron-3-nano | qwen3-30b | +|---|---:|---:|---:|---:|---:| +| business | 0.7529 | 0.7452 | 0.8137 | 0.7617 | **0.8631** | +| law | 0.4532 | 0.4405 | 0.4142 | 0.4714 | **0.5450** | +| psychology | 0.7306 | 0.7168 | 0.7206 | 0.7556 | **0.7757** | +| biology | 0.8410 | 0.8536 | 0.8536 | 0.8438 | **0.8870** | +| chemistry | 0.7420 | 0.7482 | 0.8269 | 0.7889 | **0.8763** | +| history | 0.6273 | 0.6010 | 0.5906 | 0.6089 | **0.6483** | +| other | 0.6504 | 0.6353 | 0.6461 | 0.6526 | **0.7370** | +| health | 0.6883 | 0.6601 | 0.7237 | 0.7152 | **0.7665** | +| economics | 0.7820 | 0.7761 | 0.7998 | 0.7773 | **0.8483** | +| math | 0.8653 | 0.8564 | 0.9112 | 0.8756 | **0.9445** | +| physics | 0.7852 | 0.7814 | 0.8276 | 0.7921 | **0.8961** | +| computer science | 0.7268 | 0.7341 | 0.8146 | 0.7756 | **0.8439** | +| philosophy | 0.5892 | 0.6132 | 0.6192 | 0.5972 | **0.6854** | +| engineering | 0.5057 | 0.4902 | 0.5944 | 0.5304 | **0.7678** | +| **平均** | 0.7025 | 0.6956 | 0.7343 | 0.7180 | **0.8038** | + +
+ +--- + +## 使い方 + +### 必要環境 + +- GPU: 推奨 **A100 80GB ×2 以上 / H100 80GB ×2 以上**(bfloat16・MoE expert parallel 動作時) + - 単一 80GB GPU でも `tensor-parallel-size=1` で動作可能ですが、KV キャッシュ確保のため `--max-model-len` を下げる必要がある場合があります。 +- CUDA 12.4+ +- Python 3.10+ + +### 1. transformers での推論 + +HuggingFace transformers ベースのパイプラインに組み込みたい場合は、以下のように直接ロードして使用できます。なお transformers から直接生成すると、出力には思考プロセス用の特殊トークン(`<|channel|>analysis` や `<|channel|>final` など)がそのまま含まれるため、思考と最終回答を分離して扱いたい場合は前述の vLLM + cookbook 構成を利用するか、出力をパースしてください。 + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1" + +tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", + trust_remote_code=True, +) + +messages = [ + {"role": "user", "content": "日本の宇宙開発の歴史について教えてください。"}, +] + +# chat_template により思考用プロンプトが付与されます +input_ids = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_tensors="pt", +).to(model.device) + +with torch.no_grad(): + output_ids = model.generate( + input_ids, + max_new_tokens=4096, + do_sample=True, + temperature=0.7, + top_p=0.95, + pad_token_id=tokenizer.eos_token_id, + ) + +generated = output_ids[0][input_ids.shape[-1]:] +print(tokenizer.decode(generated, skip_special_tokens=False)) +``` + +### 2. vLLM での推論(推奨) + +LLM-jp-4 系のモデルは、独自の Reasoning フォーマット(`<|channel|>final` などの特殊トークンによる思考プロセス出力)を採用しているため、素の vLLM ではそのまま正しく serve することができません。公式の [`llm-jp/llm-jp-4-cookbook`](https://github.com/llm-jp/llm-jp-4-cookbook) を利用することが推奨されています。 + +#### セットアップ + +```bash +# 1. vLLM 0.17 以降をインストール +pip install "vllm>=0.17.0" + +# 2. LLM-jp-4 cookbook を clone +git clone https://github.com/llm-jp/llm-jp-4-cookbook.git +cd llm-jp-4-cookbook/llmjp4_vllm +``` + +#### vLLM サーバの起動 + +```bash +python example_cli.py serve third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1 \ + --host 0.0.0.0 \ + --port 8000 \ + --served-model-name llm-jp-4-kappa \ + --trust-remote-code \ + --dtype bfloat16 \ + --tensor-parallel-size 2 \ + --gpu-memory-utilization 0.85 \ + --max-model-len 65536 \ + --reasoning-parser llmjp4 \ + --enable-expert-parallel +``` + +主なオプションの意味: + +| オプション | 説明 | +|---|---| +| `--reasoning-parser llmjp4` | LLM-jp-4 thinking 用の reasoning parser を有効化。**必須** | +| `--enable-expert-parallel` | MoE の expert parallel を有効化(マルチ GPU で推奨) | +| `--tensor-parallel-size` | テンソル並列数。GPU 枚数に合わせて変更してください(1, 2, 4, 8 など) | +| `--max-model-len` | 最大コンテキスト長(最大 65,536) | +| `--gpu-memory-utilization` | GPU メモリ使用率の上限。OOM になる場合は下げてください | + +> **トラブルシュート: `RuntimeError: Already borrowed`** +> 環境によっては、reasoning parser の初期化時に tokenizer の競合により上記エラーが発生することがあります。その場合は cookbook 内 `llmjp4_reasoning_parser.py` の以下 2 行を、tokenizer.encode を経由しない形に置き換えてください。 +> +> ```python +> # Before +> self._reasoning_end_prefix = tokenizer.encode("<|channel|>final") +> self._reasoning_prefill = tokenizer.encode("<|start|>assistant") +> +> # After +> self._reasoning_end_prefix = [9, 2520] +> self._reasoning_prefill = [10, 12811] +> ``` + +#### OpenAI 互換 API で叩く + +```bash +curl http://localhost:8000/v1/chat/completions \ + -H "Content-Type: application/json" \ + -d '{ + "model": "llm-jp-4-kappa", + "messages": [ + {"role": "user", "content": "整数 a, b が a^2 + b^2 = 50 を満たすとき、(a, b) の組み合わせを全て求めてください。"} + ], + "max_tokens": 4096, + "temperature": 0.7 + }' +``` + +Python (OpenAI SDK) からも同様に呼び出せます。`--reasoning-parser llmjp4` を有効にしているため、思考プロセスは `reasoning_content` フィールドに、最終回答は `content` フィールドに分離されて返ります。 + +```python +from openai import OpenAI + +client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") + +resp = client.chat.completions.create( + model="llm-jp-4-kappa", + messages=[ + {"role": "user", "content": "再帰関数を使ってフィボナッチ数列の n 番目の値を返す Python 関数を書いてください。"} + ], + max_tokens=4096, + temperature=0.7, +) + +msg = resp.choices[0].message +print("=== 思考プロセス ===") +print(getattr(msg, "reasoning_content", "")) +print("=== 最終回答 ===") +print(msg.content) +``` + +--- + +## 注意事項 + +本モデルは **研究目的で公開されているモデル** です。出力の正確性・安全性・倫理性は保証されず、事実と異なる内容(ハルシネーション)や不適切な内容を生成する可能性があります。商用利用やミッションクリティカルな用途での使用は想定していません。本モデルの利用により生じたいかなる損害についても開発者は責任を負いません。ライセンスはベースモデル(`llm-jp/llm-jp-4-32b-a3b-thinking`)の条件も併せて確認・遵守してください。 + +## ライセンス + +本モデルは **Apache License 2.0** のもとで公開されます。ベースモデル `llm-jp/llm-jp-4-32b-a3b-thinking` のライセンス・利用規約も併せて遵守してください。 + +## 謝辞 + +- ベースモデルを公開してくださっている [LLM-jp プロジェクト](https://llm-jp.nii.ac.jp/) +- データを公開してくださっている[NVIDIA](https://huggingface.co/nvidia) +- 評価フレームワーク [`swallow-llm/swallow-evaluation-instruct`](https://github.com/swallow-llm/swallow-evaluation-instruct) を公開してくださっている [Swallow プロジェクト](https://swallow-llm.github.io/index.ja.html) + +をはじめとする皆様に最大の感謝を申し上げます。 + +## 引用 + +```bibtex +@misc{llm-jp-4-kappa-32b-a3b-v0_1, + title = {llm-jp-4-kappa-32b-a3b-v0.1}, + author = {third-intelligence}, + year = {2026}, + howpublished = {\url{https://huggingface.co/third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1}} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..90daff8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,63 @@ +{#- + Simplified Harmony chat template for GRPO training (no tool support). + Based on the official llm-jp-4 chat_template.jinja. +-#} +{#- System Message Construction -#} +{%- macro build_system_message() -%} +{%- if model_identity is not defined %} +{%- set model_identity = "You are LLM-jp-4, a large language model trained by LLM-jp." %} +{%- endif %} +{{- model_identity + "\n" -}} +{%- if knowledge_cutoff is not defined %} +{%- set knowledge_cutoff = "2025-12" %} +{%- endif %} +{{- "Knowledge cutoff: " + knowledge_cutoff + "\n" -}} +{%- if conversation_start_date is not defined %} +{%- set conversation_start_date = "2026-04-14" %} +{%- endif %} +{{- "Current date: " + conversation_start_date + "\n\n" }} +{%- if reasoning_effort is not defined %} +{%- set reasoning_effort = "medium" %} +{%- endif %} +{{- "Reasoning: " + reasoning_effort + "\n\n" }} +{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }} +{%- endmacro -%} + +{#- Main Template Logic -#} +{{- "<|start|>system<|message|>" }} +{{- build_system_message() }} +{{- "<|end|>" }} + +{%- if messages[0].role == "developer" or messages[0].role == "system" %} +{%- set developer_message = messages[0].content %} +{%- set loop_messages = messages[1:] %} +{%- else %} +{%- set developer_message = "" %} +{%- set loop_messages = messages %} +{%- endif %} + +{%- if developer_message %} +{{- "<|start|>developer<|message|>" }} +{{- "# Instructions\n\n" }} +{{- developer_message }} +{{- "<|end|>" }} +{%- endif %} + +{%- for message in loop_messages -%} +{%- if message.role == 'assistant' -%} +{%- if loop.last and not add_generation_prompt %} +{%- if "thinking" in message %} +{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }} +{%- endif %} +{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }} +{%- else %} +{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }} +{%- endif %} +{%- elif message.role == 'user' -%} +{{- "<|start|>user<|message|>" + message.content + "<|end|>" }} +{%- endif -%} +{%- endfor -%} + +{%- if add_generation_prompt -%} +<|start|>assistant +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..96a808c --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "decoder_sparse_step": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.006, + "intermediate_size": 7680, + "max_position_embeddings": 65536, + "max_window_layers": 32, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 960, + "norm_topk_prob": true, + "num_attention_heads": 40, + "num_experts": 128, + "num_experts_per_tok": 8, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "output_router_logits": false, + "pad_token_id": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 500000, + "router_aux_loss_coef": 0.01, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 196608 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9dd7eb8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 4, + "transformers_version": "4.57.6", + "use_cache": false +} diff --git a/llmjp4_harmony.py b/llmjp4_harmony.py new file mode 100644 index 0000000..6d23fd8 --- /dev/null +++ b/llmjp4_harmony.py @@ -0,0 +1,129 @@ +# Generic parser for OpenAI Harmony format. + +from dataclasses import dataclass +from enum import Enum +from typing import Iterator, Sequence + +from transformers import PreTrainedTokenizerBase as TokenizerLike + + +class HarmonyMessageEndType(Enum): + INCOMPLETE = 0 + END = 1 + CALL = 2 + + +@dataclass(frozen=True) +class HarmonySequence: + """A data class representing a sequence of tokens in the Harmony format.""" + token_ids: list[int] + start: int # Start position of the sequence in the original token sequence + + +@dataclass(frozen=True) +class HarmonyMessage: + """A data class representing a message in the Harmony format.""" + end: HarmonyMessageEndType + role: HarmonySequence | None = None + channel: HarmonySequence | None = None + constrain: HarmonySequence | None = None + content: HarmonySequence | None = None + + +class HarmonyMessageParser: + """A parser that performs lexical analysis to extract Harmony messages.""" + + def __init__(self, tokenizer: TokenizerLike): + vocab = tokenizer.get_vocab() + self._begin_map = { + vocab["<|start|>"]: "role", + vocab["<|channel|>"]: "channel", + vocab["<|constrain|>"]: "constrain", + vocab["<|message|>"]: "content", + } + self._end_map = { + vocab["<|end|>"]: HarmonyMessageEndType.END, + vocab["<|return|>"]: HarmonyMessageEndType.END, + vocab["<|call|>"]: HarmonyMessageEndType.CALL, + } + + def iter_messages(self, token_ids: Sequence[int]) -> Iterator[HarmonyMessage]: + """ + Parse given token ids into messages. + + Args: + token_ids: A sequence of token ids to be parsed. + + Yields: + Detected HarmonyMessages. + """ + + message_dict: dict[str, HarmonySequence] = {} + section: str | None = None # None indicates out-of-message. + text_ids: list[int] = [] + text_start: int | None = None + + for token_position, token_id in enumerate(token_ids): + if token_id in self._begin_map: + if section is not None: + message_dict[section] = HarmonySequence( + token_ids=text_ids, + start=text_start, + ) + section = self._begin_map[token_id] + text_ids = [] + text_start = token_position + 1 + + elif token_id in self._end_map: + if section is not None: + message_dict[section] = HarmonySequence( + token_ids=text_ids, + start=text_start, + ) + + yield HarmonyMessage(**message_dict, end=self._end_map[token_id]) + + message_dict = {} + section = None + text_ids = [] + text_start = None + + else: + if section is not None: + text_ids.append(token_id) + + if section is not None: + message_dict[section] = HarmonySequence( + token_ids=text_ids, + start=text_start, + ) + yield HarmonyMessage(**message_dict, end=HarmonyMessageEndType.INCOMPLETE) + + def get_all_messages(self, token_ids: Sequence[int]) -> list[HarmonyMessage]: + """ + Parse given token ids into messages. + + Args: + token_ids: A sequence of token ids to be parsed. + + Returns: + A list of detected HarmonyMessages. + """ + return list(self.iter_messages(token_ids)) + + def reverse_iter_messages(self, token_ids: Sequence[int]) -> Iterator[HarmonyMessage]: + """ + Parse given token ids into messages in reverse order. + + Args: + token_ids: A sequence of token ids to be parsed. + + Yields: + Detected HarmonyMessages in reverse order. + """ + end_position = len(token_ids) + + for i in range(len(token_ids) - 1, -1, -1): + if token_ids[i] == self._start_id: + yield next(self.iter_messages(token_ids[i:end_position])) + end_position = i diff --git a/llmjp4_tokenizer.py b/llmjp4_tokenizer.py new file mode 100644 index 0000000..60f99e0 --- /dev/null +++ b/llmjp4_tokenizer.py @@ -0,0 +1,101 @@ +# llm-jp-4 tokenizer + +from collections.abc import Sequence +import os + +from transformers import LlamaTokenizerFast +from tokenizers import Tokenizer + +from .llmjp4_harmony import HarmonyMessageParser, HarmonyMessage + + +class Llmjp4Tokenizer(LlamaTokenizerFast): + _HARMONY_TOKENS: set[str] = { + "<|start|>", + "<|message|>", + "<|channel|>", + "<|constrain|>", + "<|end|>", + "<|return|>", + "<|call|>", + } + + # NOTE(odashi): + # Response schemas are not recognized automatically. + # We need to define them manually. + # https://github.com/huggingface/trl/issues/4609 + _RESPONSE_SCHEMA = { + "type": "object", + "properties": { + "role": {"const": "assistant"}, + "content": {"type": "string", "x-regex": r"<\|channel\|>final<\|message\|>(.*?)(?:<\|end\|>|<\|return\|>|$)"}, + "thinking": {"type": "string", "x-regex": r"<\|channel\|>analysis<\|message\|>(.*?)<\|end\|>"}, + "tool_calls": { + "x-regex-iterator": r"<\|channel\|>commentary (to=functions\..*?<\|message\|>.*?)(?:<\|call\|>|$)", + "type": "array", + "items": { + "type": "object", + "properties": { + "type": {"const": "function"}, + "function": { + "type": "object", + "properties": { + "name": {"type": "string", "x-regex": r"^to=functions\.(\w+)"}, + "arguments": { + "type": "object", + "x-regex": r"<\|message\|>(.*)", + "x-parser": "json", + "additionalProperties": {"type": "any"}, + }, + }, + }, + }, + }, + }, + }, + } + + @classmethod + def convert_to_native_format(cls, **kwargs): + # NOTE(odashi): + # Workaround for transformers 5.x. + # Guaranteeing the same inner behavior with TokenizersBackend. + # https://github.com/huggingface/transformers/blob/7d9754a05193eb79b1d86aa744b622b8068008cd/src/transformers/tokenization_utils_tokenizers.py#L110-L116 + local_kwargs = dict(kwargs) + fast_tokenizer_file = local_kwargs.pop("tokenizer_file", None) + if fast_tokenizer_file is None or not os.path.isfile(fast_tokenizer_file): + raise ValueError("Tokenizer file must exist.") + + local_kwargs["tokenizer_object"] = Tokenizer.from_file(fast_tokenizer_file) + return local_kwargs + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + self.response_schema = self._RESPONSE_SCHEMA + + self._harmony_token_ids = { + self.convert_tokens_to_ids(token) + for token in self._HARMONY_TOKENS + } + + def _decode(self, token_ids: int | list[int], *args, **kwargs): + if isinstance(token_ids, int): + token_ids = [token_ids] + + result: list[str] = [] + prev_pos = 0 + + # NOTE(odashi): + # Ensure that text tokens are decoded without preceding Harmony tokens + # to avoid incorrect addition of whitespaces. + for pos, token_id in enumerate(token_ids, start=1): + if token_id in self._harmony_token_ids or pos == len(token_ids): + result.append(super()._decode(token_ids[prev_pos:pos], *args, **kwargs)) + prev_pos = pos + + return "".join(result) + + def parse_harmony_message(self, token_ids: Sequence[int]) -> list[HarmonyMessage]: + """Helper function to parse token IDs into Harmony messages.""" + return HarmonyMessageParser(self).get_all_messages(token_ids) diff --git a/model-00001-of-00013.safetensors b/model-00001-of-00013.safetensors new file mode 100644 index 0000000..e926e59 --- /dev/null +++ b/model-00001-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebd2e6ac46ed407ec5917f44d1b83997b3fe57f8aabf0be51070a2bc41e5d9c +size 4995959408 diff --git a/model-00002-of-00013.safetensors b/model-00002-of-00013.safetensors new file mode 100644 index 0000000..191d341 --- /dev/null +++ b/model-00002-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2f6ba09fda33d11c72efb03c1e93c11e02f469c8e9467b55cdead6b191c962 +size 4997602792 diff --git a/model-00003-of-00013.safetensors b/model-00003-of-00013.safetensors new file mode 100644 index 0000000..44b15f4 --- /dev/null +++ b/model-00003-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6556aefafda3e0d76756b77ea8ec4c8387521649a9788b85197bdeed552c40a4 +size 4999858104 diff --git a/model-00004-of-00013.safetensors b/model-00004-of-00013.safetensors new file mode 100644 index 0000000..be22c4a --- /dev/null +++ b/model-00004-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39228d108526bcdaf20f4bd8152dafdef7c316ef2666385e3c845c290b29292 +size 4999242896 diff --git a/model-00005-of-00013.safetensors b/model-00005-of-00013.safetensors new file mode 100644 index 0000000..4ab0f33 --- /dev/null +++ b/model-00005-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a351d88a7a4e33d47f24f4bf509f48a487ac73c60450690835251f362ff9ee +size 4998255672 diff --git a/model-00006-of-00013.safetensors b/model-00006-of-00013.safetensors new file mode 100644 index 0000000..b1f2cc9 --- /dev/null +++ b/model-00006-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f4d27b835ce5ff68b5e57e38f04d7e16a54f5bfe60e644e6a651061d2c6282 +size 4998904016 diff --git a/model-00007-of-00013.safetensors b/model-00007-of-00013.safetensors new file mode 100644 index 0000000..32f0c07 --- /dev/null +++ b/model-00007-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd612b07216adc92a5ec26e310d84ffabbd9ac95953f779787b347e77ced0c6 +size 4998569752 diff --git a/model-00008-of-00013.safetensors b/model-00008-of-00013.safetensors new file mode 100644 index 0000000..d779299 --- /dev/null +++ b/model-00008-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5523ccfdd3ff8909749cbf8623d2f855d249a143070c8201c3f4e7c128fa601 +size 4999213704 diff --git a/model-00009-of-00013.safetensors b/model-00009-of-00013.safetensors new file mode 100644 index 0000000..19e47df --- /dev/null +++ b/model-00009-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd493e9ddb2e0458821b01b6fcb89296ede0dd0d426efb756e63acd23be772d1 +size 4998245056 diff --git a/model-00010-of-00013.safetensors b/model-00010-of-00013.safetensors new file mode 100644 index 0000000..282b5e7 --- /dev/null +++ b/model-00010-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c4133cf9d1c9b92901d0505ce46c142a3fe3d2c9ef67a7c6f0cf0603048b6e +size 4998278984 diff --git a/model-00011-of-00013.safetensors b/model-00011-of-00013.safetensors new file mode 100644 index 0000000..067bd6f --- /dev/null +++ b/model-00011-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b18eeaf5272fab1d983048423b3ad4c8593c94ebc10a4431fea14960d31654 +size 4996293096 diff --git a/model-00012-of-00013.safetensors b/model-00012-of-00013.safetensors new file mode 100644 index 0000000..903b951 --- /dev/null +++ b/model-00012-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9e8cdf080598a22f94e0a8c134a15eb662e1d1ec44ba0125c5622108d8fd0b +size 4989398160 diff --git a/model-00013-of-00013.safetensors b/model-00013-of-00013.safetensors new file mode 100644 index 0000000..ddd404d --- /dev/null +++ b/model-00013-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af20dfcb6ea88ec9e7dcb5ef3e201b1ad7ccedf2e84b66bd0415e01d417a164 +size 4309790912 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ee54e39 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,12587 @@ +{ + "metadata": { + "total_parameters": 32139028992, + "total_size": 64278057984 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00013.safetensors", + "model.embed_tokens.weight": "model-00008-of-00013.safetensors", + "model.layers.0.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.0.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.0.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.1.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.10.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.10.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.10.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.100.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.100.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.100.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.101.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.101.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.101.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.102.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.102.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.103.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.103.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.103.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.104.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.104.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.105.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.105.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.105.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.106.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.106.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.106.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.107.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.107.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.107.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.108.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.108.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.108.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.109.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.109.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.109.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.11.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.110.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.110.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.110.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.111.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.111.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.111.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.112.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.112.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.112.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.113.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.113.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.113.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.114.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.114.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.115.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.115.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.115.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.116.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.116.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.116.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.117.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.118.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.118.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.119.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.119.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.119.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.12.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.12.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.12.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.120.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.120.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.121.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.121.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.121.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.122.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.122.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.122.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.123.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.123.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.123.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.124.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.124.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.124.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.125.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.125.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.125.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.126.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.126.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.126.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.127.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.127.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.13.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.13.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.13.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.14.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.14.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.14.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.15.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.15.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.15.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.16.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.16.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.16.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.17.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.17.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.17.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.18.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.18.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.18.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.19.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.19.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.19.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.2.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.2.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.20.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.20.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.21.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.21.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.21.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.22.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.22.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.22.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.23.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.23.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.23.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.24.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.24.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.24.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.25.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.25.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.26.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.26.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.27.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.27.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.27.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.28.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.28.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.28.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.29.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.29.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.29.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.3.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.3.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.30.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.30.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.31.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.31.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.32.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.32.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.32.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.33.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.33.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.33.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.34.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.34.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.34.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.35.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.35.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.35.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.36.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.36.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.36.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.37.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.37.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.38.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.38.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.38.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.39.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.4.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.4.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.40.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.40.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.41.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.41.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.42.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.42.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.42.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.43.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.43.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.43.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.44.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.44.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.44.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.45.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.45.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.45.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.46.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.46.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.46.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.47.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.47.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.48.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.48.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.48.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.49.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.49.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.5.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.5.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.50.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.50.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.50.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.51.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.51.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.51.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.52.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.52.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.52.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.53.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.53.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.53.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.54.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.54.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.54.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.55.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.55.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.56.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.56.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.57.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.57.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.58.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.58.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.59.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.59.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.59.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.6.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.6.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.60.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.60.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.61.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.61.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.61.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.62.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.62.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.62.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.63.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.63.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.64.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.64.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.65.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.65.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.65.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.66.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.66.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.67.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.67.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.67.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.68.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.68.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.68.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.69.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.69.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.69.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.7.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.7.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.70.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.70.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.71.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.71.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.71.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.72.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.72.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.72.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.73.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.74.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.74.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.74.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.75.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.75.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.75.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.76.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.76.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.76.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.77.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.77.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.78.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.78.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.78.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.79.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.0.mlp.experts.79.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.8.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.8.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.80.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.80.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.80.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.81.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.81.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.81.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.82.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.82.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.82.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.83.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.83.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.83.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.84.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.84.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.84.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.85.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.85.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.85.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.86.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.86.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.86.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.87.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.87.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.88.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.88.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.88.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.0.mlp.experts.89.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.9.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.9.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.9.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.90.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.90.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.90.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.91.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.91.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.92.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.92.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.93.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.mlp.experts.93.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.93.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.94.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.0.mlp.experts.94.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.94.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.95.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.95.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.95.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.96.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.96.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.0.mlp.experts.96.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.0.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.experts.97.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.0.mlp.experts.97.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.mlp.experts.98.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.98.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.0.mlp.experts.98.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.experts.99.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.0.mlp.experts.99.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.mlp.experts.99.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.0.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.1.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.11.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.13.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.gate.weight": "model-00013-of-00013.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.17.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.18.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.19.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.2.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.20.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.mlp.gate.weight": "model-00013-of-00013.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.22.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.23.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.24.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.26.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.27.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.28.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.30.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.31.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.5.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.6.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.9.mlp.gate.weight": "model-00013-of-00013.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.norm.weight": "model-00012-of-00013.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..445f317 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,51 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "cls_token": { + "content": "<|cls|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|return|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "mask_token": { + "content": "<|mask|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "<|sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "<|unk|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1cbe7b6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac381ce8e5664fa1a196b943018b6fee4543f49ba87b1b6454cc1b53b23ece7 +size 12868535 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..114941d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2845 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "<|unk|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|return|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "<|mask|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "<|cls|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|eod|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "8": { + "content": "<|constrain|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "9": { + "content": "<|channel|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "10": { + "content": "<|start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "11": { + "content": "<|end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "12": { + "content": "<|message|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "13": { + "content": "<|call|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "14": { + "content": "<|reserved_006|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "15": { + "content": "<|reserved_007|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "16": { + "content": "<|reserved_008|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "17": { + "content": "<|reserved_009|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "18": { + "content": "<|reserved_010|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "19": { + "content": "<|reserved_011|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "20": { + "content": "<|reserved_012|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "21": { + "content": "<|reserved_013|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "22": { + "content": "<|reserved_014|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "23": { + "content": "<|reserved_015|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "24": { + "content": "<|reserved_016|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "25": { + "content": "<|reserved_017|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "26": { + "content": "<|reserved_018|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "27": { + "content": "<|reserved_019|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "28": { + "content": "<|reserved_020|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "29": { + "content": "<|reserved_021|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "30": { + "content": "<|reserved_022|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "31": { + "content": "<|reserved_023|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32": { + "content": "<|reserved_024|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "33": { + "content": "<|reserved_025|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "34": { + "content": "<|reserved_026|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "35": { + "content": "<|reserved_027|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "36": { + "content": "<|reserved_028|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "37": { + "content": "<|reserved_029|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "38": { + "content": "<|reserved_030|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "39": { + "content": "<|reserved_031|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "40": { + "content": "<|reserved_032|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "41": { + "content": "<|reserved_033|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "42": { + "content": "<|reserved_034|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "43": { + "content": "<|reserved_035|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "44": { + "content": "<|reserved_036|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "45": { + "content": "<|reserved_037|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "46": { + "content": "<|reserved_038|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "47": { + "content": "<|reserved_039|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "48": { + "content": "<|reserved_040|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "49": { + "content": "<|reserved_041|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "50": { + "content": "<|reserved_042|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "51": { + "content": "<|reserved_043|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "52": { + "content": "<|reserved_044|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "53": { + "content": "<|reserved_045|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "54": { + "content": "<|reserved_046|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "55": { + "content": "<|reserved_047|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "56": { + "content": "<|reserved_048|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "57": { + "content": "<|reserved_049|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "58": { + "content": "<|reserved_050|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "59": { + "content": "<|reserved_051|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "<|reserved_052|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "<|reserved_053|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "<|reserved_054|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "<|reserved_055|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "<|reserved_056|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "<|reserved_057|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "<|reserved_058|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "<|reserved_059|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "<|reserved_060|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "<|reserved_061|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "<|reserved_062|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "<|reserved_063|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "<|reserved_064|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "<|reserved_065|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "<|reserved_066|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "<|reserved_067|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "<|reserved_068|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "<|reserved_069|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "<|reserved_070|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "<|reserved_071|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "<|reserved_072|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "<|reserved_073|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "<|reserved_074|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "<|reserved_075|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "<|reserved_076|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "<|reserved_077|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "<|reserved_078|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "<|reserved_079|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "<|reserved_080|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "<|reserved_081|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "<|reserved_082|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "<|reserved_083|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "<|reserved_084|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "<|reserved_085|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "<|reserved_086|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "<|reserved_087|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "<|reserved_088|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "<|reserved_089|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "<|reserved_090|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "<|reserved_091|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "<|reserved_092|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "<|reserved_093|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "<|reserved_094|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "<|reserved_095|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "<|reserved_096|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "105": { + "content": "<|reserved_097|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "<|reserved_098|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "<|reserved_099|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "<|reserved_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "109": { + "content": "<|reserved_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "110": { + "content": "<|reserved_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "111": { + "content": "<|reserved_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "112": { + "content": "<|reserved_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "113": { + "content": "<|reserved_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "114": { + "content": "<|reserved_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "115": { + "content": "<|reserved_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "116": { + "content": "<|reserved_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "117": { + "content": "<|reserved_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "118": { + "content": "<|reserved_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "119": { + "content": "<|reserved_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "120": { + "content": "<|reserved_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "121": { + "content": "<|reserved_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "122": { + "content": "<|reserved_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "123": { + "content": "<|reserved_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "124": { + "content": "<|reserved_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "125": { + "content": "<|reserved_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "126": { + "content": "<|reserved_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "127": { + "content": "<|reserved_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128": { + "content": "<|reserved_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "129": { + "content": "<|reserved_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "130": { + "content": "<|reserved_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "131": { + "content": "<|reserved_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "132": { + "content": "<|reserved_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "133": { + "content": "<|reserved_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "134": { + "content": "<|reserved_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "135": { + "content": "<|reserved_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "136": { + "content": "<|reserved_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "137": { + "content": "<|reserved_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "138": { + "content": "<|reserved_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "139": { + "content": "<|reserved_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "140": { + "content": "<|reserved_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "141": { + "content": "<|reserved_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "142": { + "content": "<|reserved_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "143": { + "content": "<|reserved_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "144": { + "content": "<|reserved_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "145": { + "content": "<|reserved_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "146": { + "content": "<|reserved_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "147": { + "content": "<|reserved_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "148": { + "content": "<|reserved_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "149": { + "content": "<|reserved_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "150": { + "content": "<|reserved_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151": { + "content": "<|reserved_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "152": { + "content": "<|reserved_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "153": { + "content": "<|reserved_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154": { + "content": "<|reserved_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "155": { + "content": "<|reserved_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "156": { + "content": "<|reserved_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "157": { + "content": "<|reserved_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "158": { + "content": "<|reserved_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "159": { + "content": "<|reserved_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "160": { + "content": "<|reserved_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "161": { + "content": "<|reserved_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "162": { + "content": "<|reserved_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "163": { + "content": "<|reserved_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "164": { + "content": "<|reserved_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "165": { + "content": "<|reserved_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "166": { + "content": "<|reserved_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "167": { + "content": "<|reserved_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "168": { + "content": "<|reserved_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "169": { + "content": "<|reserved_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "170": { + "content": "<|reserved_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "171": { + "content": "<|reserved_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "172": { + "content": "<|reserved_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "173": { + "content": "<|reserved_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "174": { + "content": "<|reserved_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "175": { + "content": "<|reserved_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "176": { + "content": "<|reserved_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "177": { + "content": "<|reserved_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "178": { + "content": "<|reserved_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "179": { + "content": "<|reserved_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "180": { + "content": "<|reserved_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "181": { + "content": "<|reserved_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "182": { + "content": "<|reserved_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "183": { + "content": "<|reserved_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "184": { + "content": "<|reserved_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "185": { + "content": "<|reserved_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "186": { + "content": "<|reserved_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "187": { + "content": "<|reserved_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "188": { + "content": "<|reserved_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "189": { + "content": "<|reserved_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "190": { + "content": "<|reserved_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "191": { + "content": "<|reserved_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "192": { + "content": "<|reserved_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "193": { + "content": "<|reserved_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "194": { + "content": "<|reserved_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "195": { + "content": "<|reserved_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "196": { + "content": "<|reserved_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "197": { + "content": "<|reserved_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "198": { + "content": "<|reserved_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "199": { + "content": "<|reserved_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200": { + "content": "<|reserved_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "201": { + "content": "<|reserved_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "202": { + "content": "<|reserved_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "203": { + "content": "<|reserved_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "204": { + "content": "<|reserved_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "205": { + "content": "<|reserved_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "206": { + "content": "<|reserved_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "207": { + "content": "<|reserved_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "208": { + "content": "<|reserved_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "209": { + "content": "<|reserved_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "210": { + "content": "<|reserved_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "211": { + "content": "<|reserved_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "212": { + "content": "<|reserved_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "213": { + "content": "<|reserved_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "214": { + "content": "<|reserved_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "215": { + "content": "<|reserved_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "216": { + "content": "<|reserved_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "217": { + "content": "<|reserved_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "218": { + "content": "<|reserved_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "219": { + "content": "<|reserved_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "220": { + "content": "<|reserved_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "221": { + "content": "<|reserved_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "222": { + "content": "<|reserved_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "223": { + "content": "<|reserved_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "224": { + "content": "<|reserved_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "225": { + "content": "<|reserved_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "226": { + "content": "<|reserved_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "227": { + "content": "<|reserved_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "228": { + "content": "<|reserved_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "229": { + "content": "<|reserved_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "230": { + "content": "<|reserved_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "231": { + "content": "<|reserved_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "232": { + "content": "<|reserved_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "233": { + "content": "<|reserved_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "234": { + "content": "<|reserved_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "235": { + "content": "<|reserved_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "236": { + "content": "<|reserved_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "237": { + "content": "<|reserved_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "238": { + "content": "<|reserved_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "239": { + "content": "<|reserved_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "240": { + "content": "<|reserved_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "241": { + "content": "<|reserved_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "242": { + "content": "<|reserved_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "243": { + "content": "<|reserved_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "244": { + "content": "<|reserved_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "245": { + "content": "<|reserved_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "246": { + "content": "<|reserved_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "247": { + "content": "<|reserved_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "248": { + "content": "<|reserved_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "249": { + "content": "<|reserved_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250": { + "content": "<|reserved_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "251": { + "content": "<|reserved_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "252": { + "content": "<|reserved_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "253": { + "content": "<|reserved_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "254": { + "content": "<|reserved_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255": { + "content": "<|reserved_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "256": { + "content": "<|reserved_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "257": { + "content": "<|reserved_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "258": { + "content": "<|reserved_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "259": { + "content": "<|reserved_251|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "260": { + "content": "<|reserved_252|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261": { + "content": "<|reserved_253|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "262": { + "content": "<|reserved_254|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "263": { + "content": "<|reserved_255|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "264": { + "content": "<|reserved_256|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "265": { + "content": "<|reserved_257|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "266": { + "content": "<|reserved_258|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "267": { + "content": "<|reserved_259|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "268": { + "content": "<|reserved_260|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "269": { + "content": "<|reserved_261|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "270": { + "content": "<|reserved_262|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "271": { + "content": "<|reserved_263|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "272": { + "content": "<|reserved_264|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "273": { + "content": "<|reserved_265|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "274": { + "content": "<|reserved_266|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "275": { + "content": "<|reserved_267|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "276": { + "content": "<|reserved_268|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "277": { + "content": "<|reserved_269|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "278": { + "content": "<|reserved_270|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "279": { + "content": "<|reserved_271|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "280": { + "content": "<|reserved_272|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "281": { + "content": "<|reserved_273|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "282": { + "content": "<|reserved_274|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "283": { + "content": "<|reserved_275|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "284": { + "content": "<|reserved_276|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "285": { + "content": "<|reserved_277|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "286": { + "content": "<|reserved_278|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "287": { + "content": "<|reserved_279|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "288": { + "content": "<|reserved_280|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "289": { + "content": "<|reserved_281|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "290": { + "content": "<|reserved_282|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "291": { + "content": "<|reserved_283|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "292": { + "content": "<|reserved_284|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "293": { + "content": "<|reserved_285|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "294": { + "content": "<|reserved_286|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "295": { + "content": "<|reserved_287|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "296": { + "content": "<|reserved_288|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "297": { + "content": "<|reserved_289|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "298": { + "content": "<|reserved_290|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "299": { + "content": "<|reserved_291|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "300": { + "content": "<|reserved_292|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "301": { + "content": "<|reserved_293|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "302": { + "content": "<|reserved_294|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "303": { + "content": "<|reserved_295|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "304": { + "content": "<|reserved_296|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "305": { + "content": "<|reserved_297|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "306": { + "content": "<|reserved_298|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "307": { + "content": "<|reserved_299|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "308": { + "content": "<|reserved_300|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "309": { + "content": "<|reserved_301|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "310": { + "content": "<|reserved_302|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "311": { + "content": "<|reserved_303|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "312": { + "content": "<|reserved_304|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "313": { + "content": "<|reserved_305|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "314": { + "content": "<|reserved_306|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "315": { + "content": "<|reserved_307|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "316": { + "content": "<|reserved_308|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "317": { + "content": "<|reserved_309|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "318": { + "content": "<|reserved_310|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "319": { + "content": "<|reserved_311|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "320": { + "content": "<|reserved_312|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "321": { + "content": "<|reserved_313|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "322": { + "content": "<|reserved_314|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "323": { + "content": "<|reserved_315|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "324": { + "content": "<|reserved_316|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "325": { + "content": "<|reserved_317|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "326": { + "content": "<|reserved_318|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "327": { + "content": "<|reserved_319|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "328": { + "content": "<|reserved_320|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "329": { + "content": "<|reserved_321|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "330": { + "content": "<|reserved_322|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "331": { + "content": "<|reserved_323|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "332": { + "content": "<|reserved_324|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "333": { + "content": "<|reserved_325|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "334": { + "content": "<|reserved_326|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "335": { + "content": "<|reserved_327|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "336": { + "content": "<|reserved_328|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "337": { + "content": "<|reserved_329|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "338": { + "content": "<|reserved_330|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "339": { + "content": "<|reserved_331|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "340": { + "content": "<|reserved_332|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "341": { + "content": "<|reserved_333|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "342": { + "content": "<|reserved_334|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "343": { + "content": "<|reserved_335|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "344": { + "content": "<|reserved_336|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "345": { + "content": "<|reserved_337|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "346": { + "content": "<|reserved_338|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "347": { + "content": "<|reserved_339|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "348": { + "content": "<|reserved_340|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "349": { + "content": "<|reserved_341|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "350": { + "content": "<|reserved_342|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "351": { + "content": "<|reserved_343|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "auto_map": { + "AutoTokenizer": [ + "llmjp4_tokenizer.Llmjp4Tokenizer", + null + ] + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": false, + "cls_token": "<|cls|>", + "eod_token": "<|eod|>", + "eos_token": "<|return|>", + "extra_ids": 0, + "extra_special_tokens": {}, + "legacy": true, + "mask_token": "<|mask|>", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|endoftext|>", + "sep_token": "<|sep|>", + "sp_model_kwargs": {}, + "tokenizer_class": "Llmjp4Tokenizer", + "unk_token": "<|unk|>", + "use_default_system_prompt": false +}