commit 503b2871d14c61e5ffa666ee2d8bf637e742b4d4 Author: ModelHub XC Date: Wed Aug 26 02:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jvonrad/Qwen-2.5-7B-grpo-bonus5-ablation Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0d84582 --- /dev/null +++ b/README.md @@ -0,0 +1,16 @@ +--- +base_model: Qwen/Qwen2.5-7B +tags: + - grpo + - cross-lingual + - ablation +--- + +# Qwen-2.5-7B-grpo-bonus5-ablation + +GRPO all_correct_bonus ablation on Qwen2.5-7B, trained on the WIKI-FACT / +PolyFact cross-lingual factual-recall task (see +[jvonrad/Lost-in-Mistranslation](https://github.com/jvonrad/Lost-in-Mistranslation)). +`--all_correct_bonus 5.0` (all other hyperparameters match the paper's main +GRPO run). Evaluated in `results/qwen-2.5-7b-grpo-bonus5-ablation_polyfact_consistency.json` and +`results/qwen-2.5-7b-grpo-bonus5-ablation_gmmlu_lite_consistency.json` in the repo above. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..28028c0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..5e50eb0 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.13.0", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c140cb5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 151643, + "do_sample": false, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "transformers_version": "5.13.0" +} diff --git a/model-00001-of-00016.safetensors b/model-00001-of-00016.safetensors new file mode 100644 index 0000000..8f962bc --- /dev/null +++ b/model-00001-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be8567a86b9f8fdf251358a5757baf1e45239e4ba2ed2bb04d81d824a7031c5 +size 1089994880 diff --git a/model-00002-of-00016.safetensors b/model-00002-of-00016.safetensors new file mode 100644 index 0000000..64ea9e0 --- /dev/null +++ b/model-00002-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6fd723552764c41a811bc5700a78a1ab05985636cfae471f66da9e01eb3df4 +size 1089994896 diff --git a/model-00003-of-00016.safetensors b/model-00003-of-00016.safetensors new file mode 100644 index 0000000..4380c73 --- /dev/null +++ b/model-00003-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cf289258a42adc4969af14b6e2ad8e04cc0b514936c9a817caf58bdbe3117a +size 932241160 diff --git a/model-00004-of-00016.safetensors b/model-00004-of-00016.safetensors new file mode 100644 index 0000000..7437471 --- /dev/null +++ b/model-00004-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91018fd0e9e5a018ac43f9ab3b101c02bf4affa785b26b603ed057e6a77cef4 +size 932233888 diff --git a/model-00005-of-00016.safetensors b/model-00005-of-00016.safetensors new file mode 100644 index 0000000..f937fe9 --- /dev/null +++ b/model-00005-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefb77ab7520f6d27baf043876435e00107e68569635e45ca9914db680279bb0 +size 932233888 diff --git a/model-00006-of-00016.safetensors b/model-00006-of-00016.safetensors new file mode 100644 index 0000000..4227e48 --- /dev/null +++ b/model-00006-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d505a04e63916fbd9e0e6f0366b78d26a095dc2e1f0f67be3930e1482372be +size 932233888 diff --git a/model-00007-of-00016.safetensors b/model-00007-of-00016.safetensors new file mode 100644 index 0000000..13fdba3 --- /dev/null +++ b/model-00007-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14cc480afddd5886b93978cf89eabfc8dd17c94fbb261ae3009a244cb594debb +size 932233880 diff --git a/model-00008-of-00016.safetensors b/model-00008-of-00016.safetensors new file mode 100644 index 0000000..c158f5b --- /dev/null +++ b/model-00008-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2adaea50d6704ebfad8e74ab92f6e1b6605c53521c1505fa37785dc35584b35f +size 932233912 diff --git a/model-00009-of-00016.safetensors b/model-00009-of-00016.safetensors new file mode 100644 index 0000000..dca7d69 --- /dev/null +++ b/model-00009-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e4e58f7e59d6b66b3d9de665e95ce5564ea70ff48ea3768cd783508b221b02 +size 932233912 diff --git a/model-00010-of-00016.safetensors b/model-00010-of-00016.safetensors new file mode 100644 index 0000000..7a3e8fe --- /dev/null +++ b/model-00010-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d42429469866ebcbd6ca6db76ba7b29645f45fa4127c188140ff57c4798ef3 +size 932233912 diff --git a/model-00011-of-00016.safetensors b/model-00011-of-00016.safetensors new file mode 100644 index 0000000..42b2304 --- /dev/null +++ b/model-00011-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c0beeaf179baae916a2ee78ba1908c35b14f29aebe17247997c423918db216 +size 932233912 diff --git a/model-00012-of-00016.safetensors b/model-00012-of-00016.safetensors new file mode 100644 index 0000000..2a6e4f1 --- /dev/null +++ b/model-00012-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41909bc05e7a1398279fb1f00cdb875d26e440fd36e98ae718d9864e558f1975 +size 932233912 diff --git a/model-00013-of-00016.safetensors b/model-00013-of-00016.safetensors new file mode 100644 index 0000000..1a0cd69 --- /dev/null +++ b/model-00013-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72bf2c8c7ed8c968b5c864cf4f94df367ca649c0b60f9ce7890fee0409ae827 +size 932233912 diff --git a/model-00014-of-00016.safetensors b/model-00014-of-00016.safetensors new file mode 100644 index 0000000..92b31c6 --- /dev/null +++ b/model-00014-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e00457b9777dd8c6a463c1fa82bb24fce1a28f8a579a1d225e59c39c31a1ae +size 932233912 diff --git a/model-00015-of-00016.safetensors b/model-00015-of-00016.safetensors new file mode 100644 index 0000000..1eab1c9 --- /dev/null +++ b/model-00015-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ad0008a21a2448334ee89de50a2bb4deaf8d766f3769ea51d47d6797009e2f +size 932233912 diff --git a/model-00016-of-00016.safetensors b/model-00016-of-00016.safetensors new file mode 100644 index 0000000..3891ec3 --- /dev/null +++ b/model-00016-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd9517e43f81e2ae67671df8cf19469b83552a3b06a947e43924c3d678c1d16 +size 932233896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..f68e87b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_parameters": 7615616512, + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00016.safetensors", + "model.embed_tokens.weight": "model-00002-of-00016.safetensors", + "model.layers.0.input_layernorm.weight": "model-00003-of-00016.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00016.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", + "model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.input_layernorm.weight": "model-00008-of-00016.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", + "model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.input_layernorm.weight": "model-00009-of-00016.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", + "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.input_layernorm.weight": "model-00010-of-00016.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", + "model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.input_layernorm.weight": "model-00011-of-00016.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", + "model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.input_layernorm.weight": "model-00012-of-00016.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.input_layernorm.weight": "model-00013-of-00016.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", + "model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.input_layernorm.weight": "model-00014-of-00016.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", + "model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.input_layernorm.weight": "model-00015-of-00016.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", + "model.layers.26.input_layernorm.weight": "model-00015-of-00016.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.input_layernorm.weight": "model-00016-of-00016.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00016.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", + "model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00016.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.input_layernorm.weight": "model-00006-of-00016.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", + "model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.input_layernorm.weight": "model-00007-of-00016.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", + "model.norm.weight": "model-00016-of-00016.safetensors" + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1127e12 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}