Error on get_vision_tower

#3
by Clip-AI - opened

AttributeError: 'InternVLChatModel' object has no attribute 'get_vision_tower'

Any ideas on how to get past this? I saw there might be a version error here: https://github.com/haotian-liu/LLaVA/issues/15 - but not sure how to solve with InternVideo2_5; you can comment it out, it's not necessary.

Clip-AI changed discussion status to closed

I've encountered a similar problem, did you find a solution?

hi @Clip-AI @Ghaser do u solve it? i meet this problem too. btw, i use transformers.__version__: 4.47.1.

Sign up or log in to comment