注册并分享邀请链接,可获得视频播放与邀请奖励。

Badr Youbi Idrissi
@byoubii
加入 August 2015
133 正在关注    308 粉丝
What happens if we make language models predict several tokens ahead instead of only the next one? In this paper, we show that multi-token prediction boosts language model training efficiency. 🧵 1/11 Paper: Joint work with @FabianGloeckle
显示更多
0
14
540
95
转发到社区