Modailities param in LLaVA-NeXT documentation #391
+2
−0
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
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Outdated suggestions cannot be applied.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.
The llava model requires the modalities parameter to be broadcasted to the batch size, otherwise the zip statement on line 442 in llava/model/llava_arch.py reduces the batch size to 1 (the default length of this parameter). Not having this in the .generate call leads to batches of size 1 to be generated even when a larger batch size is passed in.
I think adding this to the documentation would make it a little more clear. Or maybe doing auto broadcasting of the modalities parameter if the input is a batch and this parameter isn't changed by the user.