commit fade959aab1a94899895f446fc2f34d608f1f30f Author: ModelHub XC Date: Tue Sep 15 06:42:16 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-seed51485 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..172093b --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3be194032d8086a13b2e14fa7e69eb658b1f1eafd1f89e3a63c4f6d5c4d0138 +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..f0e20fe --- /dev/null +++ b/training_logs.json @@ -0,0 +1 @@ +[{"step": 10, "loss": 1.304317092895508, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 20, "loss": 0.5906851291656494, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 30, "loss": 0.4765478610992432, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 40, "loss": 0.44742236137390134, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 50, "loss": 0.4228936195373535, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 60, "loss": 0.40297327041625974, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 70, "loss": 0.43561463356018065, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 80, "loss": 0.3981126546859741, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 90, "loss": 0.3981296539306641, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 100, "loss": 0.40607318878173826, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 110, "loss": 0.37249059677124025, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 120, "loss": 0.38126506805419924, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 130, "loss": 0.38782098293304446, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 140, "loss": 0.34850349426269533, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 150, "loss": 0.3707123279571533, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 160, "loss": 0.3465543746948242, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 170, "loss": 0.35498015880584716, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 180, "loss": 0.32308776378631593, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 190, "loss": 0.3149308681488037, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 200, "loss": 0.3478273868560791, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 210, "loss": 0.33159313201904295, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 220, "loss": 0.2999429225921631, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 230, "loss": 0.31390283107757566, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 240, "loss": 0.30716571807861326, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 250, "loss": 0.3191326379776001, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 260, "loss": 0.29768877029418944, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 270, "loss": 0.30010459423065183, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 280, "loss": 0.2930797576904297, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 290, "loss": 0.2715853929519653, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 300, "loss": 0.2688523530960083, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 310, "loss": 0.2819363594055176, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 320, "loss": 0.27516348361968995, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 330, "loss": 0.28518970012664796, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 340, "loss": 0.26887667179107666, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 350, "loss": 0.26174776554107665, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 360, "loss": 0.2567643642425537, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 370, "loss": 0.2537543296813965, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 380, "loss": 0.26965739727020266, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 390, "loss": 0.25830726623535155, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 400, "loss": 0.25205016136169434, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 410, "loss": 0.2598124027252197, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 420, "loss": 0.2627146005630493, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 430, "loss": 0.22081785202026366, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 440, "loss": 0.2659233331680298, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 450, "loss": 0.2452850818634033, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 460, "loss": 0.2360771417617798, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 470, "loss": 0.25672695636749265, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 480, "loss": 0.24548156261444093, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 490, "loss": 0.24623219966888427, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 500, "loss": 0.24939169883728027, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 510, "loss": 0.24791436195373534, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 520, "loss": 0.2331639051437378, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 530, "loss": 0.224328875541687, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 540, "loss": 0.23612029552459718, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 550, "loss": 0.231048321723938, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 560, "loss": 0.2558417797088623, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 570, "loss": 0.24767036437988282, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 580, "loss": 0.23930580615997316, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 590, "loss": 0.22322700023651124, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 600, "loss": 0.22329294681549072, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 610, "loss": 0.2205190420150757, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 620, "loss": 0.22011816501617432, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 630, "loss": 0.23144159317016602, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 640, "loss": 0.24716100692749024, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 650, "loss": 0.2271784543991089, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 660, "loss": 0.22915887832641602, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 670, "loss": 0.20206758975982667, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 680, "loss": 0.23357675075531006, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 690, "loss": 0.24131085872650146, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 700, "loss": 0.22732675075531006, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 710, "loss": 0.22025933265686035, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 720, "loss": 0.23735322952270507, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 730, "loss": 0.21972739696502686, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 740, "loss": 0.2080148458480835, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 750, "loss": 0.2116328477859497, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}] \ No newline at end of file