Support llama3.2vl(WIP). #5555
Draft
Support llama3.2vl(WIP). #5555
+85
โ1
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
hiyouga
reviewed
Sep 26, 2024
marko1616
force-pushed
the
feat/llama3.2vl
branch
from
a3a23ac
to
b0e6f98
Compare
hiyouga
reviewed
Sep 26, 2024
hiyouga
reviewed
Sep 26, 2024
| images = [Image.open(image) if isinstance(image, str) else image for image in images] | ||
| image_features = processor.image_processor(images) | ||
| _ = image_features.pop("num_tiles") | ||
| image_features = {k: v if isinstance(v, torch.Tensor) else torch.tensor(v) for k, v in image_features.items()} |
There was a problem hiding this comment.
There was a problem hiding this comment.
That is because we can't get text at get_mm_inputs how do you think to fix this? Like add a new stage or add text input to get_mm_inputs.
There was a problem hiding this comment.
yep, we should do some work here
hiyouga
reviewed
Sep 26, 2024
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Outdated suggestions cannot be applied.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.
๐ What does this PR do?
Support Llama-3.2-11B-Vision.
โ Before submitting
๐ Linked issues
#5549
bitsandbytes 8 bits quantization is not functional. 4 bits is okay but not 8 bits.