登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

Crusoe
@CrusoeAI
The AI factory company. We are on a mission to accelerate the abundance of energy and intelligence.
参加 January 2019
373 フォロー中    19.9K ファン
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:
もっと見る