Replace FeedforwardBlock with a correct implementation #211
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
justheuristic
approved these changes
Apr 7, 2021
There was a problem hiding this comment.
Request: changing FeedforwardBlock will alter the benchmarking performance reported here
Can you please update the performance stats there?
|
Re: benchmarks, we'll update the entire docs section when most of the pending server-side features are implemented and merged to master |
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Outdated suggestions cannot be applied.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.
Previously, we had a larger version of the FFN layer that had more parameters and ReLU as an activation. This PR replaces the default FFN layer with an implementation used in ALBERT by the transformers library as a reasonable default.