🚀 DeepSeek-R1-Distill-Qwen-14B-GRPO-Taiwan-Spirit

这是一个基于特定模型微调的版本，使用TRL进行训练，可用于文本生成任务。

🚀 快速开始

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="kartd/DeepSeek-R1-Distill-Qwen-14B-GRPO", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

📚 详细文档

训练过程

此模型使用GRPO方法进行训练，该方法在论文 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 中被提出。

框架版本

• TRL: 0.18.0.dev0
• Transformers: 4.52.0.dev0
• Pytorch: 2.6.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

📄 许可证

该模型遵循 license 许可证。

📚 引用

引用GRPO方法时，请使用以下格式：

@article{zhihong2024deepseekmath,
    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},
}

引用TRL时，请使用以下格式：

@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}