This repository has been archived by the owner on Oct 19, 2024. It is now read-only.
[BLOOM] Support encoder chunk sizes > 1 #738
Merged
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
Add unk_token_id of bloom, set special token_ids to their values in bloom for inference with bloom.
Support alpa's internal padding in attention masks to enable higher encoder chunk sizes
Remove warnings for larger encoder chunk sizes for bloom model as we are supporting them now.
Update wrapper.py
Add support for all encoder chunk sizes
Remove useless if statement as attention mask is always passed to bloom model.
merrymercy
force-pushed
the
main
branch
2 times, most recently
from
b5bdb0d to
fe6bd5f
Compare
merrymercy
approved these changes
Oct 9, 2022
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Add support for alpa's internal padding in bloom_model.py
Remove warnings on encoder chunk sizes in wrapper.py