commit 281cc5aa11eacff1d34ea5982dcf2552144c4841 Author: ModelHub XC Date: Mon Aug 24 05:39:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: M134pra/jailbreak-arena-defender 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..041bb9f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen2.5-0.5B-Instruct +library_name: transformers +model_name: jailbreak-arena-defender +tags: +- generated_from_trainer +- trl +- trackio:https://huggingface.co/spaces/M134pra/huggingface-static-18ee87 +- trackio +- grpo +licence: license +--- + +# Model Card for jailbreak-arena-defender + +This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct). +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="M134pra/jailbreak-arena-defender", 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 GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). + +### Framework versions + +- TRL: 1.2.0 +- Transformers: 5.6.2 +- Pytorch: 2.8.0 +- Datasets: 4.8.4 +- Tokenizers: 0.22.2 + +## Citations + +Cite GRPO as: + +```bibtex +@article{shao2024deepseekmath, + title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, + author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, + year = 2024, + eprint = {arXiv:2402.03300}, +} +``` + +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..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/completions/completions_00001.parquet b/completions/completions_00001.parquet new file mode 100644 index 0000000..ad7e9ec --- /dev/null +++ b/completions/completions_00001.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2bbf939596306dd2d0565990de45eab9827234c0ba4aba7e33e5641a641180 +size 20402 diff --git a/completions/completions_00002.parquet b/completions/completions_00002.parquet new file mode 100644 index 0000000..fe1e526 --- /dev/null +++ b/completions/completions_00002.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a2398ff03f61675f0b5a555317fc09de78c83b26512e02ef8ce3ebebc82507 +size 21457 diff --git a/completions/completions_00003.parquet b/completions/completions_00003.parquet new file mode 100644 index 0000000..64f0fbc --- /dev/null +++ b/completions/completions_00003.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85890b0a4957ed498349870c2469024286a475c57b3e1c710362840da96f340 +size 19097 diff --git a/completions/completions_00004.parquet b/completions/completions_00004.parquet new file mode 100644 index 0000000..0bade6f --- /dev/null +++ b/completions/completions_00004.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce967e33429ebea404a07a0fc7d2e05456182a174dedebf42504800a66d104c +size 20724 diff --git a/completions/completions_00005.parquet b/completions/completions_00005.parquet new file mode 100644 index 0000000..2acfc27 --- /dev/null +++ b/completions/completions_00005.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e41fe8ab12d900080345e98bd24c928e2c7d729104b4b2421eb0e41d13483f0 +size 20173 diff --git a/completions/completions_00006.parquet b/completions/completions_00006.parquet new file mode 100644 index 0000000..12f9732 --- /dev/null +++ b/completions/completions_00006.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623d05244fd4cb47b2365362c087a1c39c1dce115b2e49fa943db5cb8bd5d9ea +size 18475 diff --git a/completions/completions_00007.parquet b/completions/completions_00007.parquet new file mode 100644 index 0000000..0a6c1ea --- /dev/null +++ b/completions/completions_00007.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690506fe208ad374f1f7591c48045a26cbc96bc4ba8421e1aa37fcd4f64dfbdb +size 17436 diff --git a/completions/completions_00008.parquet b/completions/completions_00008.parquet new file mode 100644 index 0000000..c61c3be --- /dev/null +++ b/completions/completions_00008.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55926dffa6f9ca1f8076e0b43bbc7fca751af03d90146736f4a1816d8c18df56 +size 19059 diff --git a/completions/completions_00009.parquet b/completions/completions_00009.parquet new file mode 100644 index 0000000..0881302 --- /dev/null +++ b/completions/completions_00009.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665fecb884da89b48ffb9206ed2dfa5f241a9c6076570ad695893ba694d4186b +size 16922 diff --git a/completions/completions_00010.parquet b/completions/completions_00010.parquet new file mode 100644 index 0000000..cc36933 --- /dev/null +++ b/completions/completions_00010.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653feed193b2f0c3c77f9497b620e2fd426369e2a32434e6bac21124372100dd +size 18857 diff --git a/completions/completions_00011.parquet b/completions/completions_00011.parquet new file mode 100644 index 0000000..1bbdfaa --- /dev/null +++ b/completions/completions_00011.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a82b15e9a7003c6d1c25a55b137d667223468dfb0edbb36d73a0968c22ceec +size 22201 diff --git a/completions/completions_00012.parquet b/completions/completions_00012.parquet new file mode 100644 index 0000000..9973b6c --- /dev/null +++ b/completions/completions_00012.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8f9101eda5657868865af680be90c607115e8949d16c73520b82bb7eec877a +size 17539 diff --git a/completions/completions_00013.parquet b/completions/completions_00013.parquet new file mode 100644 index 0000000..a9b38dd --- /dev/null +++ b/completions/completions_00013.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a63895451d612b9cfabc94cd430f8b6d7939129386fc3b62c4e8e463943b5f +size 17127 diff --git a/completions/completions_00014.parquet b/completions/completions_00014.parquet new file mode 100644 index 0000000..c364303 --- /dev/null +++ b/completions/completions_00014.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b5a4db6ee47407ed7f1fe4e86e3ba7a5fb39e3388519623876c02771a946f3 +size 17180 diff --git a/completions/completions_00015.parquet b/completions/completions_00015.parquet new file mode 100644 index 0000000..f3437d9 --- /dev/null +++ b/completions/completions_00015.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91466e7df2e65f66100428276a918e8e50067c13d4d72d881ad71afd354d2a71 +size 17594 diff --git a/completions/completions_00016.parquet b/completions/completions_00016.parquet new file mode 100644 index 0000000..04fdac0 --- /dev/null +++ b/completions/completions_00016.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3d7944c2b8ad86544cdb7e381437fdde5a2c195bed596acaec4b536a0ddf6a +size 20204 diff --git a/completions/completions_00017.parquet b/completions/completions_00017.parquet new file mode 100644 index 0000000..b4a789a --- /dev/null +++ b/completions/completions_00017.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b4dcb9f6510996b1b5e6691cbf8f1c2120accae0f9f3e61bb91c25cce18196 +size 18341 diff --git a/completions/completions_00018.parquet b/completions/completions_00018.parquet new file mode 100644 index 0000000..e1ad469 --- /dev/null +++ b/completions/completions_00018.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b24ca556ecbec6949dd64becfe8249271054e08467fa60ddc25b8abc7707913 +size 19809 diff --git a/completions/completions_00019.parquet b/completions/completions_00019.parquet new file mode 100644 index 0000000..8b91e21 --- /dev/null +++ b/completions/completions_00019.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea63dfb916415167d8a224c4a94b8a2cded6f7d92715c4a368ecd11e261f9e6 +size 20373 diff --git a/completions/completions_00020.parquet b/completions/completions_00020.parquet new file mode 100644 index 0000000..e9546f8 --- /dev/null +++ b/completions/completions_00020.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78fa0d294ece4abf967f83621e79ae6581eda1185ee89311b1694be95d22b594 +size 19033 diff --git a/completions/completions_00021.parquet b/completions/completions_00021.parquet new file mode 100644 index 0000000..726b929 --- /dev/null +++ b/completions/completions_00021.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf3717c5de23cdcfe0f1bb0e47dd61cb2cfc396671b2016974f378774b701e4 +size 19192 diff --git a/completions/completions_00022.parquet b/completions/completions_00022.parquet new file mode 100644 index 0000000..dcdcc94 --- /dev/null +++ b/completions/completions_00022.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305c85c8dd19ef1b9412df51930b53e6a25f1b31180f1acc850c8e80c235bc46 +size 19909 diff --git a/completions/completions_00023.parquet b/completions/completions_00023.parquet new file mode 100644 index 0000000..70289ca --- /dev/null +++ b/completions/completions_00023.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983045f5d7777714df10027da56f8cd493f4821bbe0aba41c8ea2efcffb45911 +size 18665 diff --git a/completions/completions_00024.parquet b/completions/completions_00024.parquet new file mode 100644 index 0000000..174c580 --- /dev/null +++ b/completions/completions_00024.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da6e251d855344a3d3a953418d745b965ea6ee621ca6f133b83dc52f9a54006 +size 18361 diff --git a/completions/completions_00025.parquet b/completions/completions_00025.parquet new file mode 100644 index 0000000..64d09f2 --- /dev/null +++ b/completions/completions_00025.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20f4d08dfc1f197dd599c7bd65fc4b35810c68d75c8cd7374807c18dd31d178 +size 17041 diff --git a/config.json b/config.json new file mode 100644 index 0000000..e57f47d --- /dev/null +++ b/config.json @@ -0,0 +1,57 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "float32", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "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": "5.6.2", + "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..1b2bba9 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.6.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..06a78e4 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff208332ee07c8e0538cc753e9b4a0ee6c42b191f878aa21bae2e667fa9c725b +size 1976163472 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..fea5e75 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "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|>", + "response_schema": { + "type": "object" + }, + "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..d110621 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e9d9bd737c98f09f09bc7167c30612ea31e6bc19b3f8c21d8c0b60bf4ccca0 +size 7249