$ pip install open_clip_torch

import open_clip

model, preprocess = open_clip.create_model_from_pretrained('hf-hub:laion/CLIP-ViT-g-14-laion2B-s12B-b42K')
tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-g-14-laion2B-s12B-b42K')

import torch
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
image = preprocess(image).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs) 

Label probs: tensor([[0.0020, 0.0034, 0.9946]])