expansion adaper to allow language model for llava-next#486
Merged
Conversation
Signed-off-by: Rashed Z. Bhatti, PhD <rzbhatti@us.ibm.com>
|
The above code worked for me when combined with the config.py changes in PR #484 Output: |
ani300
approved these changes
Nov 12, 2025
JRosenkranz
reviewed
Nov 12, 2025
| ) -> Mapping[str, Any]: | ||
| new_sd = dict(input_sd) | ||
|
|
||
| # For multi model this expansion will be applicable only to the language_model |
Collaborator
There was a problem hiding this comment.
why is this expansion only applicable to a language model?
Collaborator
There was a problem hiding this comment.
I think this can work for other models not just language. @rzbhatti can you confirm? We might need to update this comment.
Contributor
Author
There was a problem hiding this comment.
We need it only for the language model in the multimodal architecture. If we do not restrict it to a language model, the adapter starts expanding the attention layers of the vision model, too.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 fixes the issue #485
For multi-model (like Granite Vision model), the expansion adapter now supports expansion applied to the language model component.
Example call: