Register and share your invite link to earn from video plays and referrals.

Crusoe
@CrusoeAI
The AI factory company. We are on a mission to accelerate the abundance of energy and intelligence.
Joined January 2019
373 Following    19.9K Followers
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:
Show more