Openrs3 GRPO Ja

🚀 OpenRS3 - GRPO - ja

OpenRS3 - GRPO - ja 是一個經過微調的模型，基於特定數據集對基礎模型進行優化，可用於文本生成等任務，為相關領域的應用提供了有力支持。

🚀 快速開始

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="stardust-eques/OpenRS-GRPO-ja", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

✨ 主要特性

• 該模型是 SakanaAI/TinySwallow - 1.5B - Instruct 在 kunishou/OpenMathInstruct - 1 - 1.8m - ja 數據集上的微調版本。
• 使用 TRL 進行訓練，訓練步數為 300。

📚 詳細文檔

訓練過程

本模型使用 GRPO 方法進行訓練，該方法在論文 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models 中被提出。

框架版本

• TRL: 0.16.0.dev0
• Transformers: 4.49.0
• Pytorch: 2.5.1
• Datasets: 3.5.0
• Tokenizers: 0.21.1

📄 許可證

本項目遵循指定的許可證（licence: license）。

📚 引用信息

引用 GRPO

@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

@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 Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

信息表格