Add option to remove bias from q,k,v projections in MHA #436
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
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D47594542 |
abhinavarora
pushed a commit
to abhinavarora/multimodal
that referenced
this pull request
Jul 19, 2023
…arch#436) Summary: Pull Request resolved: facebookresearch#436 Adds an option to remove bias q,k,v projections in MHA, This diff adds a `add_bias` arg to `MultiHeadAttentionWithCache`. The options defaults to True and will not change the behavior of existing use sites. Reviewed By: ankitade, pikapecan Differential Revision: D47594542 fbshipit-source-id: f2cea27842e2adcb264aed766895676fc723ac1b
abhinavarora
force-pushed
the
export-D47594542
branch
from
4429856
to
43e1ed1
Compare
|
This pull request was exported from Phabricator. Differential Revision: D47594542 |
Codecov ReportPatch coverage:
Additional details and impacted files@@ Coverage Diff @@
## main #436 +/- ##
==========================================
+ Coverage 68.59% 68.65% +0.05%
==========================================
Files 169 169
Lines 11338 11350 +12
==========================================
+ Hits 7777 7792 +15
+ Misses 3561 3558 -3
☔ View full report in Codecov by Sentry. |
…arch#436) Summary: Pull Request resolved: facebookresearch#436 Adds an option to remove bias q,k,v projections in MHA, This diff adds a `add_bias` arg to `MultiHeadAttentionWithCache`. The options defaults to True and will not change the behavior of existing use sites. Reviewed By: ankitade, pikapecan Differential Revision: D47594542 fbshipit-source-id: 667680dd238efb7ecc3531d28da9cfe8f631f2b4
abhinavarora
force-pushed
the
export-D47594542
branch
from
43e1ed1
to
ff92860
Compare
|
This pull request was exported from Phabricator. Differential Revision: D47594542 |
|
This pull request has been merged in 1940623. |
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.
Summary: Adds an option to remove bias q,k,v projections in MHA, This diff adds a
add_biasarg toMultiHeadAttentionWithCache. The options defaults to True and will not change the behavior of existing use sites.Reviewed By: ankitade, pikapecan
Differential Revision: D47594542