commit f8f53233c9ec43a1f7205b8246e61bf29651de92 Author: ModelHub XC Date: Sat Jun 13 09:17:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic 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..4044251 --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +base_model: anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic +library_name: transformers +model_name: OpenMath-Nemotron-1.5B-PruneAgnostic +tags: +- generated_from_trainer +- sft +- trl +licence: license +--- + +# Model Card for OpenMath-Nemotron-1.5B-PruneAgnostic + +This model is a fine-tuned version of [anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic](https://huggingface.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with SFT. + +### Framework versions + +- TRL: 0.29.0 +- Transformers: 5.0.0 +- Pytorch: 2.10.0+cu128 +- Datasets: 4.0.0 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..2cfe475 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,21 @@ + {%- if messages[0]['role'] == 'system' -%} + <|im_start|>system + {{ messages[0]['content'] | trim }}<|im_end|> + {%- else -%} + <|im_start|>system + <|im_end|> + {%- endif -%} + {%- for message in messages -%} + {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) or (message.role == 'assistant') -%} + <|im_start|>{{ message.role }} + {%- if message['role'] == 'assistant' %} + {% generation %}{{ message['content'] | trim }}<|im_end|>{% endgeneration %} + {%- else %} + {{ message['content'] | trim }}<|im_end|> + {%- endif %} + {%- endif -%} + {%- endfor -%} + {%- if add_generation_prompt %} + <|im_start|>assistant + {%- endif -%} + \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..882eca2 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "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": 21, + "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": 500000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.0.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151670 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d81914d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151645 + ], + "pad_token_id": 151643, + "transformers_version": "5.0.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0773ec5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c133ae9bf8c5cb36c8ab9f0a5a648380e7be656cf52d117586ffa65880691d2f +size 3086649992 diff --git a/runs/Mar05_22-11-48_ce3864fff349/events.out.tfevents.1772748708.ce3864fff349.3034.0 b/runs/Mar05_22-11-48_ce3864fff349/events.out.tfevents.1772748708.ce3864fff349.3034.0 new file mode 100644 index 0000000..92a8297 --- /dev/null +++ b/runs/Mar05_22-11-48_ce3864fff349/events.out.tfevents.1772748708.ce3864fff349.3034.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b000d383f4a078b567cfd4d2b3955419d5fd1dda596c93cfe501185bfac20b3 +size 5577 diff --git a/runs/Mar05_22-13-52_ce3864fff349/events.out.tfevents.1772748832.ce3864fff349.3034.1 b/runs/Mar05_22-13-52_ce3864fff349/events.out.tfevents.1772748832.ce3864fff349.3034.1 new file mode 100644 index 0000000..bde47e6 --- /dev/null +++ b/runs/Mar05_22-13-52_ce3864fff349/events.out.tfevents.1772748832.ce3864fff349.3034.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a6b0a3bf0cca07fcae422569ff4a7a5ed383cc1a2563e46fef4dd22044adc5 +size 6982 diff --git a/runs/Mar05_22-46-32_ce3864fff349/events.out.tfevents.1772750792.ce3864fff349.3034.2 b/runs/Mar05_22-46-32_ce3864fff349/events.out.tfevents.1772750792.ce3864fff349.3034.2 new file mode 100644 index 0000000..5242e67 --- /dev/null +++ b/runs/Mar05_22-46-32_ce3864fff349/events.out.tfevents.1772750792.ce3864fff349.3034.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed08fc09df905fa521d2f82ec1a0239f18642d2f08d14c41e086cbd6a5cda6b +size 6552 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e85ad4d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa0f6873d276e78d29759ff1ba764fe84358db27b39fe8501119662f4c1c55a +size 11422819 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..de52167 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_end|>", + "<|endoftext|>", + "<|im_start|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>", + "[THOUGHT]", + "[SOLUTION]", + "[RETURN]", + "", + "" + ], + "is_local": false, + "model_max_length": 131072, + "model_specific_special_tokens": {}, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..ce573c5 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ea5d5674476327823a9a7a9693976e60393832abd1151a8b279438ac31ed3d +size 5713