diff --git a/.gitattributes b/.gitattributes index 53d7257..21b3632 100644 --- a/.gitattributes +++ b/.gitattributes @@ -44,4 +44,6 @@ saved_model/**/* 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 \ No newline at end of file +*tfevents* 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 index 0934a31..5ab9036 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,49 @@ --- -license: Apache License 2.0 - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +library_name: transformers +datasets: +- agentica-org/DeepScaleR-Preview-Dataset +- agentica-org/DeepCoder-Preview-Dataset +base_model: +- nvidia/AceReason-Nemotron-14B +license: cc-by-nc-4.0 --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('Salesforce/E1-AceReason-14B') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/Salesforce/E1-AceReason-14B.git +## Introduction +E1-AceReason-14B is a language model fine-tuned from AceReason-Nemotron-14B. It is trained for Elastic Reasoning by budget-constrained rollout strategy, integrated into GRPO, which teaches the model to reason adaptively when the thinking process is cut short and generalizes effectively to unseen budget constraints without additional training. + +## Usage +For detailed usage, please refer to [repo](https://github.com/SalesforceAIResearch/Elastic-Reasoning). + +## Performance on AIME24 (Avg@16) + +Note: We did not tune the training hyperparameters. The performance may slightly differ from the results reported in the original paper due to differences in the environment setup. + +| Model | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | +|---------------|--------------|---------------|--------------|---------------|--------------|---------------|--------------|---------------|--------------|---------------| +| AceReason-Nemotron-14B | 13833 | 76.5 | - | - | - | - | - | - | - | - | +| E1-AceReason-14B | 8376 | 75.4 | 1318 | 13.3 | 1736 | 22.7 | 2660 | 33.8 | 3448 | 44.6 | + +## Performance on LiveCodeBenchv5 (Avg@8) + +Note: We did not tune the training hyperparameters. The performance may slightly differ from the results reported in the original paper due to differences in the environment setup. + +| Model | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | Tokens | Acc (%) | +|---------------|--------------|---------------|--------------|---------------|--------------|---------------|--------------|---------------|--------------|---------------| +| AceReason-Nemotron-14B | 16669 | 59.2 | - | - | - | - | - | - | - | - | +| E1-AceReason-14B | 10796 | 57.8 | 1314 | 31.3 | 1810 | 36.3 | 2743 | 40.2 | 3585 | 43.5 | + + +## Citation + + +```bibtex +@article{xu2025scalable, + title={Scalable Chain of Thoughts via Elastic Reasoning}, + author={Xu, Yuhui and Dong, Hanze and Wang, Lei and Sahoo, Doyen and Li, Junnan and Xiong, Caiming}, + journal={arXiv preprint arXiv:2505.05315}, + year={2025} +} ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +## Ethical Considerations +This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people's lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a636467 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "/fsx/home/yuhui/Elastic-Reasoning/checkpoints/deepcoder/nvidia-14b-grpo+-2k-1k-1K/actor/global_step_20", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.47.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} 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/generation_config.json b/generation_config.json new file mode 100644 index 0000000..853903d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "pad_token_id": 151643, + "transformers_version": "4.47.1" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..3e9c4d8 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6bbbc321252dbc1779380bdd0ef8fd8a263e4ab0a05694034749d9cb7207be3 +size 135 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..194b826 --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8bd19072d6744ad9f66c860ca8f40abc261987cac36d41b86cc07427e32c94b +size 135 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..9e5ce7c --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791ed9d1cb15d83adac63efd337c1f1087f2a670c62467e049a8460c2dbb6f69 +size 135 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..7bd44d7 --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ec284f24963592ab57fe97755fd82875b5be6a325b66eb10a6f412d220a74e +size 135 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..6c1a5df --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae734c029a327b32e6119ab332f590a603a1318fa0c417f55a76c13ab21980b0 +size 135 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..fa95d81 --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce228dbb6a38c48020e69b80a5afed40e5f6bf4435fe6d2e01a3000426c86a8f +size 135 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0e9b535 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,586 @@ +{ + "metadata": { + "total_size": 29540067328 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3240a49 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}