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

permute twice? #37

Open

aflyingnoob opened this issue Mar 5, 2019 · 1 comment

aflyingnoob commented Mar 5, 2019

self-attention, Q K V , Q * K has a permute for calculate attention weight, but the attention weight permute again to multiply V ?

valillon commented May 17, 2021

Related #54

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