import torch
from PIL import Image
from transformers import AutoModel, AutoFeatureExtractor, AutoTokenizer

model = AutoModel.from_pretrained("calpt/CLIP-ViT-B-32-xlm-roberta-base-laion5B-s13B-b90k", trust_remote_code=True)

processor = AutoFeatureExtractor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base")

image_input = processor(Image.open("CLIP.png"), return_tensors="pt")
text_input = tokenizer(["a diagram", "a dog", "a cat"], return_tensors="pt", padding=True)

with torch.no_grad():
    outputs = model(**image_input, **text_input)
    text_probs = (100.0 * outputs.logits_per_image.softmax(dim=-1))

print("Label probs:", text_probs)