Hi, how did it do it

by Sariel00 - opened May 5

May 5

Can the MOE model reduce the number of parameters by reducing the number of experts? How did it do it?
This may be a model suitable for edge mobile devices. Is there a model for w8a8?

shimmyshimmer

Unsloth AI org May 6

You'll need to ask @kalomaze for that. He might be able to help with that :)

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