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.

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

typo/bug in pooler? #4

Closed
N0r9st opened this issue Feb 16, 2024 · 1 comment
Closed

typo/bug in pooler? #4

N0r9st opened this issue Feb 16, 2024 · 1 comment

Comments

@N0r9st
Copy link

N0r9st commented Feb 16, 2024

Probably enumerate(self.blocks, 1) ?

in attentive_pooler.py

for layer_id, layer in enumerate(1, self.blocks):
        rescale(layer.attn.proj.weight.data, layer_id + 1)
        rescale(layer.mlp.fc2.weight.data, layer_id + 1)
@MidoAssran
Copy link
Contributor

Yes that's correct, thanks for the catch. Will update that!

In the released configs we only use one block so the issue does not appear.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants