mtmd : use RMS norm for InternVL 3 38B and 78B mmproj #13459
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
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Outdated suggestions cannot be applied.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.
Follow-up to #13443 - in my original PR I was only checking the config file for the actual ViT and failed to realize the norm type was also different, since it wasn't included in that specific config. See referenced PR for more information.
Due to the norm type not being stored in the gguf metadata, we check the hidden size and block count instead.
Quick test
Before (topk=1, greedy sampling, black and white image)
After (topk=1, greedy sampling, same image)