metadata
license: mit
library_name: open_clip
pipeline_tag: zero-shot-image-classification
TeCoA (Mao et al. (2023)) CLIP ViT-L/14 model.
Supervised adversarial fine-tuning from Openai CLIP initialization on ImageNet with infinity-norm and radius 4/255.
model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:chs20/tecoa4-clip')