How to use UCSC-VLAA/openvision2-vit-large-patch14-336-vision-only with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:UCSC-VLAA/openvision2-vit-large-patch14-336-vision-only') tokenizer = open_clip.get_tokenizer('hf-hub:UCSC-VLAA/openvision2-vit-large-patch14-336-vision-only')
nielsr