trlx
PublicA repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Creat:2022-10-04T03:42:40
Update:2025-03-24T17:08:57
4.7K
Stars
3
Stars Increase
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)