+
+
+
++ Paper Link👁️ +
+ + +## 1. Introduction + +The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro. + +
+ 
+
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 +## 5. License +This code repository is licensed under [MIT License](LICENSE). The use of DeepSeek-R1 models is also subject to [MIT License](LICENSE). DeepSeek-R1 series (including Base and Chat) supports commercial use and distillation. + +## 6. Citation +``` +@misc{deepseekai2025deepseekr1incentivizingreasoningcapability, + title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, + author={DeepSeek-AI}, + year={2025}, + eprint={2501.12948}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2501.12948}, +} +``` + +## 7. Contact +If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com). diff --git a/config.json b/config.json new file mode 100644 index 0000000..57c7962 --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "rope_type": "yarn", + "factor": 4.0, + "original_max_position_embeddings": 32768 + }, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/figures/benchmark.png b/figures/benchmark.png new file mode 100644 index 0000000..7af4bd3 Binary files /dev/null and b/figures/benchmark.png differ diff --git a/model-00001-of-000002.safetensors b/model-00001-of-000002.safetensors new file mode 100644 index 0000000..4012b8d --- /dev/null +++ b/model-00001-of-000002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3446e0ca6c563365fca3d5df0209de37852b8ff9048dfd00fd03a642825d5fb +size 135 diff --git a/model-00002-of-000002.safetensors b/model-00002-of-000002.safetensors new file mode 100644 index 0000000..6807590 --- /dev/null +++ b/model-00002-of-000002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b63fca70c9ffe9467391efc7a09510ec165bebfe925fcd36471635755f15be +size 135 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..9ca4d22 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_size": 16381470720 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-000002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-000002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-000002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-000002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-000002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-000002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-000002.safetensors", + "model.norm.weight": "model-00002-of-000002.safetensors", + "lm_head.weight": "model-00002-of-000002.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5e6be21 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d3a3ffb1ff38eb6a22f8a2d207306bfa3ea2499ff70df4baeaa559bf7453c7 +size 7032822 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c24fd8e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 131072, + "pad_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "sp_model_kwargs": {}, + "unk_token": null, + "tokenizer_class": "LlamaTokenizerFast", + "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='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- 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｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}" +} \ No newline at end of file
+ 
+ 
+ 
+ 
+ 
+