https://github.com/jianzhnie/open-r1

The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1
https://github.com/jianzhnie/open-r1

deepseek-r1 deepseek-v3 grpo llm rlhf

Last synced: 7 months ago
JSON representation

The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1

• Host: GitHub
• URL: https://github.com/jianzhnie/open-r1
• Owner: jianzhnie
• License: apache-2.0
• Created: 2023-03-08T03:56:10.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2025-02-07T10:01:51.000Z (8 months ago)
• Last Synced: 2025-02-08T06:58:25.444Z (8 months ago)
• Topics: deepseek-r1, deepseek-v3, grpo, llm, rlhf
• Language: Python
• Homepage: https://jianzhnie.github.io/llmtech
• Size: 810 KB
• Stars: 199
• Watchers: 12
• Forks: 38
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Open-R1: An open-source implementation of DeepSeek-R1

[![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/jianzhnie/Open-R1/blob/main/LICENSE)

[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/release/python-390/)

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

## Introduction

`Open-R1` is a open-source library that allows you to train a hyper-personalized DeepSeek-R1-like model using your own data and the least amount of compute possible.

## License

`Open-R1` is released under the Apache 2.0 license.

## Acknowledgements

We appreciate the work by many open-source contributors, especially:

- [Hugging Face](https://huggingface.co/)

- [Vicuna](https://github.com/lm-sys/FastChat/)