Transformers How to use ostris/CLIP-ViT-H-14-448 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("zero-shot-image-classification", model="ostris/CLIP-ViT-H-14-448")
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 AutoTokenizer, CLIPVisionModelWithProjection
tokenizer = AutoTokenizer.from_pretrained("ostris/CLIP-ViT-H-14-448")
model = CLIPVisionModelWithProjection.from_pretrained("ostris/CLIP-ViT-H-14-448", device_map="auto") 
