deepseek-ai / deepseek-ai/DeepSeek-Math
GRPO as part of HF TRL?
Open
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 592
- PR merge metrics
- No merged PRs in 30d
Description
Would be cool to see this compared to other methods
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points. Start by clarifying whether the request is for a comparison of GRPO with other methods or integration with Hugging Face TRL; completion criteria and relevant project locations are not specified.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100