NF4 model inference

by Melody32768 - opened Jan 20

Jan 20

Hello, for the nf4 model, I see nf4 quantization in the weights section, will the input be quantized to nf4 when inferring the model? Is fp4 the same?

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

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment