commit e8e1e4f039ed0b53526391e8ae9eb09ad3789c1e Author: ModelHub XC Date: Wed Jul 15 14:20:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7cf4e8b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.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 + +model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +tokenizer.json 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..f954017 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: +- elyza/ELYZA-japanese-Llama-2-7b +- elyza/ELYZA-japanese-Llama-2-7b-instruct +license: llama2 +language: +- ja +tags: +- mergekit +- merge +- MoE +--- +# ELYZA-japanese-Llama-2-MoE-2x7B-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[elyza/ELYZA-japanese-Llama-2-7b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b)と、そのinstruction tuningモデルである[elyza/ELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct) +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/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1-GGUF) + +以下2モデルを利用しています。 +- [elyza/ELYZA-japanese-Llama-2-7b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b) +- [elyza/ELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct) + +## ライセンス +元モデルの通り、Llama2ライセンスを継承します。 + +Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. + +## ベンチマーク +ベースとしたELYZA-japanese-Llama-2-7b-instruct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| +|---|---|---|---|---|---|---|---|---|---|---| +| ELYZA-japanese-Llama-2-7b-instruct | 7B | **2.4** | 3.3 | **5.7** | 1.8 | **4.7** | 4.7 | 4.8 | **6.2** | 4.2125 | +| This model | 2x7B | 2.2 | **6.4** | 5.5 | **2.1** | 3.9 | **5.5** | **5.3** | 5.9 | **4.6000** | + +![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** +``` +"""[INST] <> +あなたは誠実で優秀な日本人のアシスタントです。 +<> + +{instruction} [/INST]""" +``` + +## Description +This model is created using MoE (Mixture of Experts) through mergekit based on [elyza/ELYZA-japanese-Llama-2-7b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b) and [elyza/ELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct). + +[Click here for the GGUF version](https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1-GGUF) + +It utilizes the following two models: +- [elyza/ELYZA-japanese-Llama-2-7b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b) +- [elyza/ELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct) + +## License +This model inherit the Llama2 license. + +Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. + +## Benchmark +The results of this model and the base ELYZA-japanese-Llama-2-7b-instruct on japanese-mt-bench are as follows. +(Single turn) +|Model|Size|Coding|Extraction|Humanities|Math|Reasoning|Roleplay|STEM|Writing|avg_score| +|---|---|---|---|---|---|---|---|---|---|---| +| ELYZA-japanese-Llama-2-7b-instruct | 7B | **2.4** | 3.3 | **5.7** | 1.8 | **4.7** | 4.7 | 4.8 | **6.2** | 4.2125 | +| This model | 2x7B | 2.2 | **6.4** | 5.5 | **2.1** | 3.9 | **5.5** | **5.3** | 5.9 | **4.6000** | + +![レーダーチャート](./japanese_mt_bench.png) + +**Prompt used for benchmark** +``` +"""[INST] <> +あなたは誠実で優秀な日本人のアシスタントです。 +<> + +{instruction} [/INST]""" +``` + +## Merge config +[mergekit_config.yml](./mergekit_moe_config.yml) +```yaml +base_model: ./ELYZA-japanese-Llama-2-7b-instruct +gate_mode: random +dtype: bfloat16 +experts: + - source_model: ./ELYZA-japanese-Llama-2-7b-instruct + positive_prompts: [] + - source_model: ./ELYZA-japanese-Llama-2-7b + positive_prompts: [] +tokenizer_source: model:./ELYZA-japanese-Llama-2-7b-instruct +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..45a59cc --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "./ELYZA-japanese-Llama-2-7b-instruct", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "mixtral", + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "num_local_experts": 2, + "output_router_logits": false, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "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": 32000 +} 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..5427fe1 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..5190036 --- /dev/null +++ b/mergekit_moe_config.yml @@ -0,0 +1,9 @@ +base_model: ./ELYZA-japanese-Llama-2-7b-instruct +gate_mode: random +dtype: bfloat16 +experts: + - source_model: ./ELYZA-japanese-Llama-2-7b-instruct + positive_prompts: [] + - source_model: ./ELYZA-japanese-Llama-2-7b + positive_prompts: [] +tokenizer_source: model:./ELYZA-japanese-Llama-2-7b-instruct diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..d8a3dd8 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1e1fcb32d546b783d1caea75b862382a416d1452266287544572905e9d6b16 +size 9978516240 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..7994502 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5420ccef9e6af54dc3b63d24cd95259d8b9dad0cb2e606bab716187469517ba +size 9949148736 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..322566c --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f005be5af95bc39fe06ef097600b74af5ff40379c2654b04a651aac01eb53f69 +size 2206785744 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b37b8e2 --- /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-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "lm_head.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.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..ca61a61 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c1b254b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7696e1d138f5958e759507047a2f171ebbc09c45fd47e3d8feee8eaa5ec6a814 +size 1842866 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..13fd7ac --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "max_length": 3269, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "stride": 0, + "tokenizer_class": "LlamaTokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": "", + "use_default_system_prompt": false +}