Set multimodal status during Model Loading #7199
Merged
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
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
Merge dev branch
|
Tested with ExLlamav3 model with vision, and llama.cpp using the example model scenario in your tutorial. |
|
I realized that I did not commit the correct version of |
|
Good idea, it's indeed better to check if the model is multimodal just once instead of every call.
I can see the merit in this. To keep things simple, I'd prefer not to add it for now for loaders where it can't be True. Thanks for the excellent refactor! |
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Outdated suggestions cannot be applied.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.
[ X ] I have read the Contributing guidelines.
I'm proposing this change to make it easier for future expansion (if other loaders may support multimodal, etc).
Instead of analyzing if the model is multimodal capable on every generation, in
load_model():Falseby defaultshared.is_multimodal()->Falsein all other loader modules.