New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Pre-trained model and code for ViT #2

Open

BaohaoLiao opened this issue Dec 8, 2023 · 1 comment

BaohaoLiao commented Dec 8, 2023

Hi,

thank you very much for the release of the code. Here I have two requests.

Could you release some pre-trained models?
it's beneficial for us to take it as a first step to test the code and reproduce the reported results.
The code for ViT.
I see there is not related scripts and codes for ViT. Do you plan to release the code for ViT?

xuann6 commented Mar 1, 2024

Same here, and I am curious why the accuracy of W8A8 ViT is 69.24±6.93, which means the accuracy varies from 63~75%? Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment