Simple GRPO distilation trainer written in rust candle. Inspired by hf's trl implementation and the deepseek research paper
-
Notifications
You must be signed in to change notification settings - Fork 0
JoeruCodes/grpo
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Simple GRPO distilation trainer written in rust candle. Also contains mamba llm finetuned via GRPO
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published