Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Questions re: the DeepNorm implementation #277

Unanswered
hanqin asked this question in Q&A
Discussion options

in

the DeepNorm is calculated as
return self.layer_norm(x + self.alpha * gx)

should this be
return self.layer_norm(self.alpha * x + gx)?

this is implementation from torchscale lib
https://github.com/microsoft/torchscale/blob/4d1e0e82e5adf86dd424f1463192635b73fc8efc/torchscale/architecture/decoder.py#L130

You must be logged in to vote

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
1 participant

AltStyle によって変換されたページ (->オリジナル) /