開放
Collapse reference+learner hydra heads when using LoRa
contributions welcomefeature requestgood first issue
為什麼推薦尚無負責人 · 帶有初學者友善標籤
尚無負責人帶有初學者友善標籤提供貢獻指南
6 則留言2 個反應0 負責人
倉庫議題
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
倉庫議題
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)