How to use cs-giung/clip-vit-base-patch16-laion2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="cs-giung/clip-vit-base-patch16-laion2b") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("cs-giung/clip-vit-base-patch16-laion2b") model = AutoModelForZeroShotImageClassification.from_pretrained("cs-giung/clip-vit-base-patch16-laion2b", device_map="auto")
https://huggingface.co/cs-giung/clip-vit-base-patch16-laion2b/resolve/main/tokenizer.json
hf download hf://cs-giung/clip-vit-base-patch16-laion2b/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/cs-giung/clip-vit-base-patch16-laion2b/resolve/main/tokenizer.json
