commit 77dbf02cff43163c265b6d8dc81654c1ada45040 Author: ModelHub XC Date: Sat Jun 27 10:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mkd-hossain/keural-14.8b-stage2-vllm Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4297af3 --- /dev/null +++ b/README.md @@ -0,0 +1,192 @@ +--- +language: + - ko + - en +license: apache-2.0 +tags: + - mixtral + - moe + - korean + - english + - bilingual + - pretrained +base_model: mkd-hossain/keural-14.8b-stage2-vllm +library_name: transformers +pipeline_tag: text-generation +--- + +# Keural 14.8B — Stage 2 (vLLM Ready) + +Keural is a **14.83B parameter bilingual Korean-English Mixture-of-Experts language model** trained from scratch on Korean and English text. This repository contains the **Stage 2 annealing checkpoint** (120,000 steps total) in HuggingFace Mixtral-compatible safetensors format, ready to serve with vLLM or Transformers. + +> **Note:** This is a **base pretrained model**, not an instruction-following or chat model. SFT (Supervised Fine-Tuning) training is planned as the next stage. + +--- + +## Model Architecture + +| Property | Value | +|---|---| +| Architecture | Mixtral MoE (MixtralForCausalLM) | +| Parameters | ~14.83B total (~2.9B active per token) | +| Layers | 24 | +| Hidden size | 4096 | +| Attention heads | 32 (GQA: 8 KV heads) | +| Experts | 8 total, top-2 active per token | +| FFN intermediate size | 5632 | +| Context length | 4096 tokens | +| Vocabulary | 131,072 | +| RoPE theta | 500,000 | +| Sliding window | 512 | +| Activation | SiLU | +| dtype | bfloat16 | + +--- + +## Tokenizer + +Custom SentencePiece tokenizer trained on Korean and English text. + +| Token | String | ID | +|---|---|---| +| BOS | `` | 1 | +| EOS | `` | 2 | +| PAD | `` | 0 | +| UNK | `` | 3 | + +--- + +## Training Details + +### Stage 1 — Pretraining +- **Steps:** 100,000 +- **Tokens:** ~43 billion +- **Data:** Korean and English web text (FineWeb, WanJuan, HPLT, etc.) +- **Batch size:** Large-scale FSDP distributed training +- **Hardware:** 2× NVIDIA H200 (150GB each) +- **Learning rate:** Cosine decay from 3e-4 to 3e-5 + +### Stage 2 — Annealing (Clean Data) +- **Steps:** 20,000 (steps 100K → 120K) +- **Tokens:** ~5.16 billion (clean subset) +- **Data:** High-quality filtered Korean and English text only + - FineWeb-Edu (English) + - FineWeb2 Korean + - HPLT Korean + - WanJuan Korean +- **Learning rate:** Cosine continued ~4.8e-5 → 3e-5 +- **Purpose:** Improve output quality by annealing on clean data + +--- + +## Usage + +### vLLM (Recommended) + +Install vLLM: +```bash +pip install vllm==0.9.2 --no-build-isolation +pip install "transformers==4.57.0" +``` + +Serve as OpenAI-compatible API: +```bash +vllm serve mkd-hossain/keural-14.8b-stage2-vllm \ + --dtype bfloat16 \ + --max-model-len 4096 +``` + +Query the API: +```python +from openai import OpenAI + +client = OpenAI(base_url="http://localhost:8000/v1", api_key="token") + +response = client.completions.create( + model="mkd-hossain/keural-14.8b-stage2-vllm", + prompt="인공지능이란 무엇인가?", + max_tokens=256, + temperature=0.7, +) +print(response.choices[0].text) +``` + +### Transformers + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "mkd-hossain/keural-14.8b-stage2-vllm" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", +) + +prompt = "인공지능이란 무엇인가?" +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) + +with torch.no_grad(): + outputs = model.generate( + **inputs, + max_new_tokens=256, + temperature=0.7, + top_p=0.9, + top_k=50, + repetition_penalty=1.1, + do_sample=True, + ) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### Korean Example + +```python +prompt = "한국의 역사에 대해 설명해 주세요." +``` + +### English Example + +```python +prompt = "Explain the history of artificial intelligence." +``` + +--- + +## Limitations + +- This is a **base pretrained model** — it continues text, it does not follow instructions or answer questions in a chat format. +- Context length is limited to **4096 tokens**. +- Outputs may be repetitive or incoherent for complex reasoning tasks — SFT and RLHF training will improve this significantly. +- Not aligned or safety-filtered. Use responsibly. + +--- + +## Roadmap + +- [x] Stage 1 Pretraining — 100K steps, ~43B tokens +- [x] Stage 2 Annealing — 20K steps, ~5.16B clean tokens +- [ ] SFT (Supervised Fine-Tuning) — instruction following +- [ ] RLHF / DPO alignment +- [ ] Keural Chat model release + +--- + +## Citation + +```bibtex +@misc{keural2026, + title = {Keural: A Bilingual Korean-English MoE Language Model}, + author = {MKD Hossain}, + year = {2026}, + url = {https://huggingface.co/mkd-hossain/keural-14.8b-stage2-vllm} +} +``` + +--- + +*Trained from scratch on KT Cloud NIPA2-H200 infrastructure using FSDP distributed training.* diff --git a/config.json b/config.json new file mode 100644 index 0000000..56555a3 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "architectures": [ + "MixtralForCausalLM" + ], + "model_type": "mixtral", + "vocab_size": 131072, + "hidden_size": 4096, + "intermediate_size": 5632, + "num_hidden_layers": 24, + "num_attention_heads": 32, + "num_key_value_heads": 8, + "head_dim": 128, + "num_local_experts": 8, + "num_experts_per_tok": 2, + "max_position_embeddings": 4096, + "rope_theta": 500000.0, + "rms_norm_eps": 1e-05, + "sliding_window": 512, + "hidden_act": "silu", + "initializer_range": 0.02, + "use_cache": true, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0", + "output_router_logits": false, + "router_aux_loss_coef": 0.001, + "keural_step": 120000 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2e0f319 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "max_new_tokens": 512, + "temperature": 0.7, + "top_p": 0.9, + "top_k": 50, + "repetition_penalty": 1.1, + "do_sample": true, + "transformers_version": "4.40.0" +} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..e2842a3 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25cfee524de8d5df887db84f535ea3601a4f2a8aefec5f4764d8fa9b3e2843ac +size 4823790280 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..0ae3124 --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be4f1167b60d7d2e9648e4fd22b8af8ac42ef17d75f1352769708c6298fe0ca +size 4811210208 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..d635605 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5cfa6b9ea4d554f5a7597bcc3674be802b857c9926864e60189d4a9674075f +size 4811210248 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..18871d2 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd25c71bea4a028ab9d52881a000305cb529f700cd7a583c60ae795cff79997 +size 4811210336 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..90e3361 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0de873974953fa0f20b45f6fbb7b523061f37c1ebed83eeaabc642387b801e3 +size 4811210336 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..9bac2e8 --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b643a29ad23c2a8883f5e868d17a5b3adeb6beac2ac064a89481345058ba367 +size 4811210336 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..9bf760d --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ef23eeff25fbe8a8ca5f0f7ca3a6b509f6bd05c02ba94cc584155e7c437442 +size 1858087280 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..e4ac30a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,754 @@ +{ + "metadata": { + "total_size": 30737833984 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00007.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00007.safetensors", + "model.norm.weight": "model-00007-of-00007.safetensors", + "lm_head.weight": "model-00007-of-00007.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..95b397a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + "eos_token": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + "unk_token": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + }, + "pad_token": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..1b292cd --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b982818ea2f2057ba791e2006d17683799f1d8ceb9c91322018a638c4ec4b170 +size 2657284 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4f7b701 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,11 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "", + "pad_token": "", + "model_max_length": 4096, + "tokenizer_class": "LlamaTokenizer", + "sp_model_kwargs": {}, + "legacy": false, + "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ bos_token + '[INST] <>\\n' + message['content'] + '\\n<>\\n\\n' }}{% elif message['role'] == 'user' %}{{ message['content'] + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}" +}