Transformers How to use TJKlein/CLIP-ViT with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("zero-shot-image-classification", model="TJKlein/CLIP-ViT")
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("TJKlein/CLIP-ViT")
model = AutoModelForZeroShotImageClassification.from_pretrained("TJKlein/CLIP-ViT", device_map="auto") 
