Fix q8 weights (use uint8 for q8; int8 produces poor results)

#18

by Xenova HF staff - opened 29 days ago

base: refs/heads/main

←

from: refs/pr/18

Discussion Files changed

-2

Upload fixed q8 ONNX models (reduce_range=True, per_channel=True)06633a3e

Xenova

Hugging Face TB Research org 29 days ago

•

edited 29 days ago

Slightly better, but not great. Will play around with other settings

Upload folder using huggingface_hub0919b6ca

Fix q8 weights (use uint8 for q8; int8 produces poor results)4f13109a

Xenova changed pull request title from Upload fixed q8 ONNX models (reduce_range=True, per_channel=True) to Fix q8 weights (use uint8 for q8; int8 produces poor results) 29 days ago

Xenova changed pull request status to merged 29 days ago

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