Refactor quantization and add quantization options to masked modeling #115
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
Contributor
Author
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Contributor
Author
|
It looks like many of the failures existed on main, but I went ahead and updated the PR to fix them. |
Collaborator
|
LGTM. Thanks for the fix |
guangy10
approved these changes
Jul 29, 2025
Contributor
Author
|
One more update to fix tests/models/test_modeling_gptj.py |
Contributor
Author
|
I think the failing test is not related. Let me know if this can be merged @michaelbenayoun @echarlaix @guangy10 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
This PR refactors quantization into a common location, and adds quantization support to masked LM models (previously only available in decoder models).