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.
It has been trained using TRL.

Quick start

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.

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:

@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:

@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}
}