开放
Collapse reference+learner hydra heads when using LoRa
contributions welcomefeature requestgood first issue
为什么推荐暂无负责人 · 带有初学者友好标签
暂无负责人带有初学者友好标签提供贡献指南
6 条评论2 个反应0 负责人
仓库议题
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
仓库议题
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)