A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Why do you think that https://github.com/tatsu-lab/stanford_alpaca is a good alternative to trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Why do you think that https://github.com/tatsu-lab/stanford_alpaca is a good alternative to trlx