commit 42377a8a50dd4ba0219850d646544cd2929445f1 Author: ModelHub XC Date: Wed Sep 23 20:46:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: 1010happy/Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed88888888 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..2480968 --- /dev/null +++ b/README.md @@ -0,0 +1,201 @@ +--- +library_name: transformers +tags: +- trl +- sft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + +This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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..bf9b3c7 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "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", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..455a4d8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.14.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..9da833d --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0fd4ab2d58cf2c00f2f9d11340fbbae84849f8d2924355090dbf3e1c084f699 +size 6171927112 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..770e41d --- /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": "<|im_end|>", + "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": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/training_logs.json b/training_logs.json new file mode 100644 index 0000000..ed62fcf --- /dev/null +++ b/training_logs.json @@ -0,0 +1 @@ +[{"step": 10, "loss": 1.3048184394836426, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 20, "loss": 0.58120756149292, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 30, "loss": 0.5049255847930908, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 40, "loss": 0.44705877304077146, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 50, "loss": 0.4343238353729248, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 60, "loss": 0.42472329139709475, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 70, "loss": 0.4071381092071533, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 80, "loss": 0.40152688026428224, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 90, "loss": 0.3940366268157959, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 100, "loss": 0.39076235294342043, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 110, "loss": 0.393797492980957, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 120, "loss": 0.3570192575454712, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 130, "loss": 0.3641955375671387, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 140, "loss": 0.3687657356262207, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 150, "loss": 0.3470041751861572, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 160, "loss": 0.361341667175293, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 170, "loss": 0.3441413402557373, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 180, "loss": 0.32879109382629396, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 190, "loss": 0.3305380344390869, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 200, "loss": 0.3126821041107178, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 210, "loss": 0.31677913665771484, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 220, "loss": 0.30894775390625, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 230, "loss": 0.30592081546783445, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 240, "loss": 0.28100497722625734, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 250, "loss": 0.286671781539917, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 260, "loss": 0.2804588317871094, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 270, "loss": 0.28288559913635253, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 280, "loss": 0.28731164932250974, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 290, "loss": 0.2796638965606689, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 300, "loss": 0.2749607563018799, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 310, "loss": 0.2811314105987549, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 320, "loss": 0.2745756864547729, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 330, "loss": 0.25094640254974365, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 340, "loss": 0.2685621023178101, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 350, "loss": 0.276748514175415, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 360, "loss": 0.2744107246398926, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 370, "loss": 0.2711628913879395, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 380, "loss": 0.25817868709564207, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 390, "loss": 0.25149240493774416, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 400, "loss": 0.2586113929748535, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 410, "loss": 0.25379581451416017, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 420, "loss": 0.23310327529907227, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 430, "loss": 0.24301857948303224, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 440, "loss": 0.24452452659606932, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 450, "loss": 0.2389770746231079, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 460, "loss": 0.26532323360443116, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 470, "loss": 0.23894119262695312, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 480, "loss": 0.2298657178878784, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 490, "loss": 0.2365561008453369, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 500, "loss": 0.25436317920684814, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 510, "loss": 0.23049871921539306, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 520, "loss": 0.22834267616271972, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 530, "loss": 0.24309055805206298, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 540, "loss": 0.24293889999389648, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 550, "loss": 0.21711108684539795, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 560, "loss": 0.23380179405212403, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 570, "loss": 0.23715341091156006, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 580, "loss": 0.23097589015960693, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 590, "loss": 0.22315771579742433, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 600, "loss": 0.21901850700378417, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 610, "loss": 0.24254972934722902, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 620, "loss": 0.23186104297637938, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 630, "loss": 0.2453214406967163, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 640, "loss": 0.22088053226470947, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 650, "loss": 0.20499215126037598, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 660, "loss": 0.2405853748321533, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 670, "loss": 0.24019243717193603, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 680, "loss": 0.20989625453948973, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 690, "loss": 0.2223273515701294, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 700, "loss": 0.23197147846221924, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 710, "loss": 0.2359251022338867, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 720, "loss": 0.21879887580871582, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 730, "loss": 0.2194385290145874, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 740, "loss": 0.22065272331237792, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 750, "loss": 0.23409416675567626, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}] \ No newline at end of file