update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies

by XuebinWang - opened Sep 23

←

AMD org Sep 23

•

arc challenge (↑）: accuracy 0.6237, recovery rate 99.5%
mmlu (↑）: accuracy 0.6765, recovery rate 98.1%

XuebinWang changed pull request status to open Sep 23

XuebinWang changed pull request status to merged Sep 23

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