Add AdaptFormer #741
Merged
Add AdaptFormer #741
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
caroteu
commented
Oct 17, 2024
caroteu
commented
Oct 17, 2024
…mented flexible dropout layer
anwai98
reviewed
Dec 4, 2024
| block: nn.Module, | ||
| alpha: Optional[Union[str, float]] = "learnable_scalar", # Stable choice from our preliminary exp. | ||
| dropout: Optional[float] = None, # Does not have an obvious advantage. | ||
| projection_size: int = 64, # Stable choice from our preliminary exp. |
There was a problem hiding this comment.
With the defaults set above, there might be a case that higehr projection_size is benefitial (?)
|
Hi @constantinpape, This method is GTG from our side as well. Let us know if you spot something. |
constantinpape
approved these changes
Dec 14, 2024
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Outdated suggestions cannot be applied.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.
@anwai98 I added AdaptFormer to the PEFT methods. The number of trainable parameters for vit_b is 4.147552 (~4.15M).