Transformers How to use ostris/CLIP-H-Face-v3 with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, CLIPVisionModelWithProjection
tokenizer = AutoTokenizer.from_pretrained("ostris/CLIP-H-Face-v3")
model = CLIPVisionModelWithProjection.from_pretrained("ostris/CLIP-H-Face-v3", device_map="auto") 
