Only apply activation if transformer block is used in DIETClassifier #5626
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I think @Ghostvv wanted to place the call to the activation inside DIET conditioned on usage of transformer and not place it inside transformer? |
|
yes, let's keep transformer a "classic" transformer |
tabergma
force-pushed
the
bug-activation
branch
from
9d1802c
to
b22d618
Compare
|
@tabergma this update requires retraining the model |
|
True. I guess it is already released 🙈 |
|
that is a bit dangerous, since prediction might go haywire, because technically models can be loaded |
|
any suggestion on how to solve that? |
|
can we update docs and rerelease? |
erohmensing
changed the title
tabergma
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed changes:
Only apply activation if transformer block is used in DIETClassifier
Status (please check what you already did):
black(please check Readme for instructions)