Fix layerwise targets #36
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
bfineran
approved these changes
Jul 24, 2024
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
* Create LICENSE * Add license and description details to package * Update setup.py * Set the same ceiling for torch dep as in `sparseml` * revert --------- Co-authored-by: dbogunowicz <97082108+dbogunowicz@users.noreply.github.com>
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Outdated suggestions cannot be applied.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:
When we previously added in support for the targets/scheme UX to GPTQModifier, this overwrote an existing attribute also named targets that stored the names of the transformer layers (used for sequential updates). This PR renames targets to restore the original functionality
TEST PLAN:
Manual testing. Previously
GPTQModifier(targets="Linear", scheme="W8A8", ignore=["lm_head"], sequential_update=True)would run calibration for every linear layer rather than every transformer layer. After the fix we get the correct number of layers