CarperAI/trlxPython
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
(4,184 stars) (450 forks) (2 indexed issues) (2 open good first issues)
Repositories
Daily Newsletter
Get fresh easy issues in your inbox.
Subscribe to GoodFirstIssue Daily for newly found easy issues that are ready for beginner-friendly open source work.