patomp/thai-light-multimodal-clip-and-distill

pip install pythainlp
pip install gensim>=4.3.1
pip install git+https://github.com/openai/CLIP.git

from transformers import AutoModel

text = 'หมากำลังวิ่งในสนามหญ้า'
model = AutoModel.from_pretrained("patomp/thai-light-multimodal-clip-and-distill", trust_remote_code=True)

embeddings = model(text)
print("Text features shape:", embeddings.shape)

import torch
import clip
import requests
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
image = preprocess(image).unsqueeze(0).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)

print("Image features shape:", image_features.shape)