注册并分享邀请链接,可获得视频播放与邀请奖励。

Crusoe
@CrusoeAI
The AI factory company. We are on a mission to accelerate the abundance of energy and intelligence.
加入 January 2019
373 正在关注    19.9K 粉丝
LoRA freezes the base weights. So why store them in bf16? We keep them in mxfp4 in HBM and dequantize inside the kernel. The optimizer only touches the LoRA adapters. Up to 75% less base-weight memory, with no accuracy loss in our internal evals. ➕ The math:
显示更多