{ "license" : "MIT", "author" : "A. Radford et al.", "creationDate" : "20260611T225847Z", "description" : "CLIP (Contrastive Language-Image Pretraining) learns joint representations of images and text, enabling zero-shot image classification with natural language labels. Source: https:\/\/huggingface.co\/openai\/clip-vit-base-patch32", "assetVersion" : "2.0" }