注册并分享邀请链接,可获得视频播放与邀请奖励。

Alex Ker 🔭
@thealexker
code+words @baseten | investing in frontiers & sharing my curiosities | prev @bloombergbeta @stanfordhai @neurable.
加入 May 2018
1.3K 正在关注    13.3K 粉丝
post-training is the next frontier for scaling laws if you want to understand the efficient post-training mechanics behind open models today, I summarized all the innovations for glm-5.3 in plain english, covering environment design, architecture, as well as the rl algorithm and infra behind it:
显示更多
0
4
514
55
转发到社区