visheratin/

nllb-clip-large-siglip

from open_clip import create_model_from_pretrained, get_tokenizer
from PIL import Image
import requests
import torch

model, transform = create_model_from_pretrained("nllb-clip-large-siglip", "v1", device="cuda")

tokenizer = get_tokenizer("nllb-clip-large-siglip")

class_options = ["бабочка", "butterfly", "kat"]
class_langs = ["rus_Cyrl", "eng_Latn", "afr_Latn"]

text_inputs = []
for i in range(len(class_options)):
    tokenizer.set_language(class_langs[i])
    text_inputs.append(tokenizer(class_options[i]))
text_inputs = torch.stack(text_inputs).squeeze(1).to("cuda")

image_path = "https://huggingface.co/spaces/jjourney1125/swin2sr/resolve/main/samples/butterfly.jpg"
image = Image.open(requests.get(image_path, stream=True).raw)

image_inputs = transform(image).unsqueeze(0).to("cuda")

with torch.inference_mode():
    logits_per_image, logits_per_text = model.get_logits(image_inputs, text_inputs)

print(logits_per_image.softmax(dim=-1))