https://github.com/nevercase/qwen-grpo

This is a reproduction of deepseek thinking based on qwen and grpo trainer.
https://github.com/nevercase/qwen-grpo

Last synced: 12 months ago
JSON representation

This is a reproduction of deepseek thinking based on qwen and grpo trainer.

• Host: GitHub
• URL: https://github.com/nevercase/qwen-grpo
• Owner: neverCase
• Created: 2025-05-03T09:58:55.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-05-06T09:53:49.000Z (about 1 year ago)
• Last Synced: 2025-05-19T03:12:28.518Z (about 1 year ago)
• Language: Python
• Size: 1000 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# qwen-grpo

This is a reproduction of deepseek thinking based on qwen and grpo trainer.