CarperAI 的仓库

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

最近提交 2024年1月8日

(4,184 stars) (450 forks) (2 个已索引 issue) (2 个开放 good first issue)

每天在邮箱收到新鲜 Easy issues。