commit ff5cdc6394410f7fd728e64d7360d8108b46ae62 Author: ModelHub XC Date: Fri Sep 25 14:07:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: 1010happy/Teacher_r14_train_gptmini_all7-Qwen2-5-1-5B-seed896 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..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..7f4ad69 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "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": 12, + "num_hidden_layers": 28, + "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_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4e1b764 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "do_sample": false, + "eos_token_id": [ + 151643 + ], + "max_new_tokens": 2048, + "pad_token_id": 151643, + "transformers_version": "5.14.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0087984 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da352f1430adc3e8fb5fdd990c44c0fb2c4611b43e0b441220363fb36bec1dd +size 3087467144 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..df536e9 --- /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": 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..ccc5eda --- /dev/null +++ b/training_logs.json @@ -0,0 +1 @@ +[{"step": 10, "loss": 1.3386627197265626, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 20, "loss": 0.7140394687652588, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 30, "loss": 0.5931126117706299, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 40, "loss": 0.5248405933380127, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 50, "loss": 0.4853933811187744, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 60, "loss": 0.5008263111114502, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 70, "loss": 0.4624813079833984, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 80, "loss": 0.46820955276489257, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 90, "loss": 0.425252103805542, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 100, "loss": 0.423712158203125, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 110, "loss": 0.42192797660827636, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 120, "loss": 0.3926037311553955, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 130, "loss": 0.4026202201843262, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 140, "loss": 0.38918588161468504, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 150, "loss": 0.3951814413070679, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 160, "loss": 0.38652772903442384, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 170, "loss": 0.39199326038360593, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 180, "loss": 0.40622458457946775, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 190, "loss": 0.40969371795654297, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 200, "loss": 0.37538650035858157, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 210, "loss": 0.38541150093078613, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 220, "loss": 0.38406202793121336, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 230, "loss": 0.3863623857498169, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 240, "loss": 0.36816022396087644, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 250, "loss": 0.3649250268936157, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 260, "loss": 0.35028507709503176, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 270, "loss": 0.37735326290130616, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 280, "loss": 0.3300719976425171, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 290, "loss": 0.35694930553436277, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 300, "loss": 0.3486881971359253, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 310, "loss": 0.36569716930389407, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 320, "loss": 0.33663172721862794, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 330, "loss": 0.34145383834838866, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 340, "loss": 0.3409287929534912, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 350, "loss": 0.3265491008758545, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 360, "loss": 0.30097413063049316, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 370, "loss": 0.3355522871017456, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 380, "loss": 0.32996349334716796, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 390, "loss": 0.33097615242004397, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 400, "loss": 0.3063162088394165, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 410, "loss": 0.3182636260986328, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 420, "loss": 0.30781500339508056, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 430, "loss": 0.32373638153076173, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 440, "loss": 0.3146980285644531, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 450, "loss": 0.3138547897338867, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 460, "loss": 0.28534998893737795, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 470, "loss": 0.33708264827728274, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 480, "loss": 0.3217299222946167, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 490, "loss": 0.32792460918426514, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 500, "loss": 0.3123291254043579, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 510, "loss": 0.3283184051513672, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 520, "loss": 0.2875030517578125, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 530, "loss": 0.32058086395263674, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 540, "loss": 0.2960990905761719, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 550, "loss": 0.3107271671295166, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 560, "loss": 0.28838291168212893, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 570, "loss": 0.29188582897186277, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 580, "loss": 0.31553289890289304, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 590, "loss": 0.3005467176437378, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 600, "loss": 0.31571524143218993, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 610, "loss": 0.3000189781188965, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 620, "loss": 0.3141429901123047, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 630, "loss": 0.30292043685913084, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 640, "loss": 0.3153672456741333, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 650, "loss": 0.3047968626022339, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 660, "loss": 0.29496166706085203, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 670, "loss": 0.29726471900939944, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 680, "loss": 0.31832594871520997, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 690, "loss": 0.3001561641693115, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 700, "loss": 0.29119205474853516, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 710, "loss": 0.30280342102050783, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 720, "loss": 0.31468355655670166, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 730, "loss": 0.3102795362472534, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 740, "loss": 0.30212602615356443, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}, {"step": 750, "loss": 0.2863780975341797, "b": "teacher_2026-07-26_exp_0_p5_r7_i1"}] \ No newline at end of file