* Add an argument robust_masking to the Softmax layer to enable better numerical handling of the mask (currently if the mask violates any of the assumptions it will do numerically silly things silently).
#869
Conversation
This file contains hidden or 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
copybara-service
bot
force-pushed
the
test_831896060
branch
from
d32fe55 to
adad2c0
Compare
copybara-service
bot
changed the title
robust_masking to the Softmax layer to enable better numerical handling of the mask (currently if the mask violates any of the assumptions it will do numerically silly things silently).
copybara-service
bot
force-pushed
the
test_831896060
branch
from
adad2c0 to
8616787
Compare
copybara-service
bot
force-pushed
the
test_831896060
branch
from
8616787 to
1da4c43
Compare
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Outdated suggestions cannot be applied.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.
robust_maskingto theSoftmaxlayer to enable better numerical handling of the mask (currently if the mask violates any of the assumptions it will do numerically silly things silently).MultiHeadAttentionlayer and the model gardenTransformerEncoderBlocklayer.