commit dd21bb0db6682554dbde4600d7015f2eb4976727 Author: ModelHub XC Date: Fri Aug 28 16:16:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Aratako/Swallow-MoE-2x13B-v0.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bd1d739 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 + +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..b36bd29 --- /dev/null +++ b/README.md @@ -0,0 +1,107 @@ +--- +base_model: +- tokyotech-llm/Swallow-13b-instruct-hf +- nitky/Superswallow-13b-v0.2 +license: llama2 +language: +- ja +tags: +- mergekit +- merge +- MoE +--- +# Swallow-MoE-2x13B-v0.1 +[**English description here**](#description) + + +## 概要 +Llama-2ベースの学習済み日本語モデルである[tokyotech-llm/Swallow-13b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf)と、それを利用したマージモデルである[nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2) +を、[mergekit](https://github.com/cg123/mergekit)を使ってMoEを行い作成したモデルです。 + +[GGUF版はこちら](https://huggingface.co/Aratako/Swallow-MoE-2x13B-v0.1-GGUF) + +以下2モデルを利用しています。 +- [tokyotech-llm/Swallow-13b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf) +- [nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2) + +## ライセンス +Llama2ライセンスを継承しますが、それ以外にもこのマージモデルはLlama2ライセンス以外のライセンスの影響を受けます。 +- [nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2)の利用により、[AI2 ImpACT license](https://allenai.org/impact-license)を継承している可能性があります。詳細は元モデルの概要をご確認ください。 + +## ベンチマーク +ベースとしたSwallow-13b-instruct-hf、Superswallow-13b-v0.2と本モデルの[japanese-mt-bench](https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge)の結果は以下の通りです。 +（シングルターン） +|Model|Size|Coding|Extraction|Humanities|Math|Reasoning|Roleplay|STEM|Writing|avg_score| +|---|---|---|---|---|---|---|---|---|---|---| +| Swallow-13b-instruct-hf | 13B | 2.1 | 5.0 | 6.1 | 1.9 | 4.5 | 5.0 | 4.9 | 5.6 | 4.3875 | +| Superswallow-13b-v0.2 | 13B | **2.7** | **6.3** | **8.4** | 2.2 | **5.9** | 6.8 | 7.2 | 6.8 | 5.7875 | +| This model | 2x13B | 2.6 | 6.2 | **8.4** | **2.3** | 5.3 | **7.4** | **7.7** | **8.4** | **6.0375** | + +![レーダーチャート](./japanese_mt_bench.png) +**ベンチマークに使用したプロンプト** +- Swallow-13b-instruct-hf, Superswallow-13b-v0.2 +``` +以下に、あるタスクを説明する指示があり、それに付随する入力が更なる文脈を提供しています。リクエストを適切に完了するための回答を記述してください。 +### 指示: +{instruction} +### 応答: +``` +- Swallow-MoE-2x13B-v0.1 +``` +### 指示: +{instruction} +### 応答: +``` + +## Description +This model is created using MoE (Mixture of Experts) through mergekit based on [tokyotech-llm/Swallow-13b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf) and [nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2). + +[Click here for the GGUF version](https://huggingface.co/Aratako/Swallow-MoE-2x13B-v0.1-GGUF) + +It utilizes the following two models: +- [tokyotech-llm/Swallow-13b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf) +- [nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2) + +## License +While inheriting the Llama2 license, this merged model is also subject to other licenses due to its use of models beyond Llama2. +- Due to the use of [nitky/Superswallow-13b-v0.2](https://huggingface.co/nitky/Superswallow-13b-v0.2), it may inherit the [AI2 ImpACT license](https://allenai.org/impact-license). Please refer to the original model's overview for details. + +## Benchmark +The results of this model and the base Swallow-13b-instruct-hf, Superswallow-13b-v0.2 on japanese-mt-bench are as follows. +(Single turn) +|Model|Size|Coding|Extraction|Humanities|Math|Reasoning|Roleplay|STEM|Writing|avg_score| +|---|---|---|---|---|---|---|---|---|---|---| +| Swallow-13b-instruct-hf | 13B | 2.1 | 5.0 | 6.1 | 1.9 | 4.5 | 5.0 | 4.9 | 5.6 | 4.3875 | +| Superswallow-13b-v0.2 | 13B | **2.7** | **6.3** | **8.4** | 2.2 | **5.9** | 6.8 | 7.2 | 6.8 | 5.7875 | +| This model | 2x13B | 2.6 | 6.2 | **8.4** | **2.3** | 5.3 | **7.4** | **7.7** | **8.4** | **6.0375** | + +![レーダーチャート](./japanese_mt_bench.png) + +**Prompt used for benchmark** +- Swallow-13b-instruct-hf, Superswallow-13b-v0.2 +``` +以下に、あるタスクを説明する指示があり、それに付随する入力が更なる文脈を提供しています。リクエストを適切に完了するための回答を記述してください。 +### 指示: +{instruction} +### 応答: +``` +- Swallow-MoE-2x13B-v0.1 +``` +### 指示: +{instruction} +### 応答: +``` + +## Merge config +[mergekit_config.yml](./mergekit_moe_config.yml) +```yaml +base_model: ./Superswallow-13b-v0.2 +gate_mode: random +dtype: bfloat16 +experts: + - source_model: ./Superswallow-13b-v0.2 + positive_prompts: [] + - source_model: ./Swallow-13b-instruct-hf + positive_prompts: [] +tokenizer_source: union +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..aa811b9 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "_name_or_path": "./Superswallow-13b-v0.2", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "max_sequence_length": 4096, + "model_type": "mixtral", + "num_attention_heads": 40, + "num_experts_per_tok": 2, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "num_local_experts": 2, + "output_router_logits": false, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.38.1", + "use_cache": true, + "vocab_size": 43176 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/japanese_mt_bench.png b/japanese_mt_bench.png new file mode 100644 index 0000000..82041bd Binary files /dev/null and b/japanese_mt_bench.png differ diff --git a/mergekit_moe_config.yml b/mergekit_moe_config.yml new file mode 100644 index 0000000..4453a7f --- /dev/null +++ b/mergekit_moe_config.yml @@ -0,0 +1,9 @@ +base_model: ./Superswallow-13b-v0.2 +gate_mode: random +dtype: bfloat16 +experts: + - source_model: ./Superswallow-13b-v0.2 + positive_prompts: [] + - source_model: ./Swallow-13b-instruct-hf + positive_prompts: [] +tokenizer_source: union diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..107b9df --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3c24fc3a99c8974bd1d88ad12fb6022afb18e1dd3094c98dd9aa19eea820aa +size 9991334896 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..0728a96 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bd653ece20d530310f0950ada6d33e85dad461cf04ae8d20141709aac1d2ac +size 9956437664 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..8b7f316 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854eb969bf7977fad5fc61ed25b614705d161e4f72106205e3bf4bb5a7996dd6 +size 9883037576 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..f2ded2f --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85fecf01dd7bb57c0460b37c35440e6d3d279f12079782a305736206ef9e5851 +size 9956427328 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..f6757c2 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6e39701ba25425dad8c105f94883e9197d58089acd93e68a2b145c8c29122c +size 3461190752 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d6dfd70 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.norm.weight": "model-00001-of-00005.safetensors", "lm_head.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00005-of-00005.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..8c95e0b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e087c95 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37120ff77f62176cb54e53d2c31ed4498c6afee484eae53bd74f509c923f6351 +size 2304163 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..48d502c --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8 +size 914000 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..48e6ae0 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}