Do you have any plan to support other NVILA models such as NVILA-15B?

by Rebellions - opened Mar 13

Mar 13

Do you have any plan to support other NVILA models such as NVILA-15B?

Efficient-Large-Model org Mar 18

working on it and will post soon

tanvij

Mar 31

•

@Ligeng-Zhu Hi, any pointers on how to quantize this model to int8 weight-only precision?

Efficient-Large-Model org Apr 1

you can refer to the awq repo for quantization.

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