mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #17] GRPO implementation #15
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#15
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @hank0316 on GitHub (Jan 21, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/17
Hi Deepseek Team,
Thank you for your brilliant work! I’m currently trying to experiment with GRPO, but I couldn’t find its implementation. Do you have any plans to release the training code?
@meigel commented on GitHub (Jan 25, 2025):
https://huggingface.co/docs/trl/main/en/grpo_trainer
@github-actions[bot] commented on GitHub (Feb 25, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@syyuan2021 commented on GitHub (Mar 12, 2025):
Is the GRPO trainer on huggingface the same as in the DeepseekMath paper?
@lemonsi commented on GitHub (Aug 3, 2025):
https://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py