How does 4bit bnb quantization work on MXFP4?

by vijay120 - opened 15 days ago

15 days ago

The 20B oss model is already quantized using MXFP4. Wondering how 4bit bnb works on top of it?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment