Skip to content
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

scaling of attention in EPA module #80

Open
maunzzz opened this issue Oct 8, 2024 · 0 comments
Open

scaling of attention in EPA module #80

maunzzz opened this issue Oct 8, 2024 · 0 comments

Comments

@maunzzz
Copy link

maunzzz commented Oct 8, 2024

Hi!
I was wondering why the dot product attention is scaled by a learnable(?) weight (self.temperature, self.temperature2) before softmax instead of 1/sqrt(d) as described in the paper?

Best Regards,
Måns
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@maunzzz