Add safeguard for missing quant_state in vision models #165
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
|
Thanks @rabintiwari45 - wait bitsandbytes 4bit layers should always have |
|
Yep, in the model from the PR mentioned above, quant_state was missing |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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 adds a check to safely skip vision models that do not have the quant_state attribute, such as:
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
unsloth/granite-vision-3.2-2b
Without this check, attempting to access quant_state on these models results in an AttributeError. This update ensures robustness when loading or iterating over models in the unsloth_zoo package by printing a warning and continuing gracefully.
This pr is linked to #2701 pr in unsloth.