跳到正文
@natolambert· @natolambert · X·· 26 天前AI 评分20
AI 导读

对于那些认为蒸馏主要是 SFT 副产物、并且不清楚在 RL 定义的时代它如何变得越来越有影响力的人来说,这是一大胜利。https://t.co/PSvWtJ4Sj6

正文

Big W for people saying that distillation was mostly an SFT artifact, and how its unclear how it would become increasingly influential in an era defined by RL. https://t.co/PSvWtJ4Sj6

来源:@natolambert · x.com