search

CarperAI / trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
MIT License
4.51k stars 471 forks source link

update(requirements.txt): to the latest `transformers` & `deepspeed` #579

Open maxreciprocate opened 1 year ago

maxreciprocate commented 1 year ago

This PR updates requirements.txt with most recent versions of dependencies.

LouisCastricato commented 1 year ago

https://github.com/CarperAI/trlx/issues/580 See this issue.