ColPali
Safetensors
English
paligemma
vidore-experimental

Integrate with AutoModel

#5
by Samoed - opened

I've addded integration with AutoModel, but when I'm trying to load processor with AutoProcessor I get only GemmaTokenizerFast instead of ColPaliProcessor.

When I'm trying to load with

from colpali_engine.models import ColPaliProcessor

ColPaliProcessor.from_pretrained("vidore/colpali-v1.3-merged", trust_remote_code=True)

I recive TypeError: not a string

Samoed changed pull request status to open
Ready to merge
This branch is ready to get merged automatically.
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment