Add: documentation for enhanced save_pretrained parameters
#1377
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
|
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed. |
There was a problem hiding this comment.
Pull Request Overview
This PR introduces new documentation in docs/save_pretrained.md to explain the enhanced save_pretrained functionality with additional compression parameters.
- Provides detailed descriptions of new parameters.
- Offers complete code examples for both automatic and manual wrapping approaches.
- Includes notes on compatibility with loading compressed models.
rahul-tuli
requested review from
brian-dellabetta,
kylesayrs,
dsikka,
shanjiaz and
robertgshaw2-redhat
and removed request for
robertgshaw2-redhat
kylesayrs
previously approved these changes
Apr 23, 2025
dsikka
reviewed
Apr 23, 2025
dsikka
requested changes
Apr 23, 2025
Signed-off-by: Rahul Tuli <[email protected]>
Signed-off-by: Rahul Tuli <[email protected]>
rahul-tuli
force-pushed
the
add-save-pretrained-doc
branch
from
c6e7bbd to
38faad8
Compare
dsikka
approved these changes
Apr 23, 2025
brian-dellabetta
approved these changes
Apr 23, 2025
kylesayrs
pushed a commit
that referenced
this pull request
Apr 29, 2025
This PR adds comprehensive documentation for the compression parameters available in the enhanced `save_pretrained` method. These parameters are critical for users working with model compression but were previously undocumented. ## Changes - Adds a new `docs/save_pretrained.md` file explaining: - How the enhanced `save_pretrained` method works - Detailed descriptions of all compression parameters - Code examples showing common usage patterns - Notes on compatibility with loading compressed models ## Benefits - **Better User Experience:** Users can clearly understand all available options - **Improved Onboarding:** New users can quickly learn how to save compressed models - **Comprehensive Examples:** Shows different approaches for saving models with compression This documentation supports [ticket](https://issues.redhat.com/browse/INFERENG-578) and will help users leverage the full capabilities of the compression functionality in the save process. --------- Signed-off-by: Rahul Tuli <[email protected]>
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.
This PR adds comprehensive documentation for the compression parameters available in the enhanced
save_pretrainedmethod. These parameters are critical for users working with model compression but were previously undocumented.Changes
docs/save_pretrained.mdfile explaining:save_pretrainedmethod worksBenefits
This documentation supports ticket and will help users leverage the full capabilities of the compression functionality in the save process.