Vit B 16 SigLIP2

🚀 ViT-B-16-SigLIP2 Model Card

This is a SigLIP 2 Vision-Language model trained on WebLI, which has been converted for use in OpenCLIP from the original JAX checkpoints in Big Vision. It is designed for zero-shot image classification tasks.

🚀 Quick Start

The following steps and code example will help you quickly start using the ViT-B-16-SigLIP2 model.

✨ Features

• Model Type: Contrastive Image-Text, Zero-Shot Image Classification.
• Original: https://github.com/google-research/big_vision
• Dataset: WebLI
• Papers:
  • SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features: https://arxiv.org/abs/2502.14786
  • Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343

📦 Installation

To use this model, you need to install the required libraries. Make sure open-clip-torch >= 2.31.0 and timm >= 1.0.15 are installed.

💻 Usage Examples

Basic Usage

import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image
from open_clip import create_model_from_pretrained, get_tokenizer # works on open-clip-torch >= 2.31.0, timm >= 1.0.15

model, preprocess = create_model_from_pretrained('hf-hub:timm/ViT-B-16-SigLIP2')
tokenizer = get_tokenizer('hf-hub:timm/ViT-B-16-SigLIP2')

image = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)

labels_list = ["a dog", "a cat", "a donut", "a beignet"]
text = tokenizer(labels_list, context_length=model.context_length)

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image, normalize=True)
    text_features = model.encode_text(text, normalize=True)
    text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)

zipped_list = list(zip(labels_list, [100 * round(p.item(), 3) for p in text_probs[0]]))
print("Label probabilities: ", zipped_list)

📚 Documentation

The model details and usage are described above. For more information, please refer to the original papers and the source code repository.

📄 License

This model is licensed under the Apache-2.0 license.

📚 Citation

@article{tschannen2025siglip,
  title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features},
  author={Tschannen, Michael and Gritsenko, Alexey and Wang, Xiao and Naeem, Muhammad Ferjad and Alabdulmohsin, Ibrahim and Parthasarathy, Nikhil and Evans, Talfan and Beyer, Lucas and Xia, Ye and Mustafa, Basil and H'enaff, Olivier and Harmsen, Jeremiah and Steiner, Andreas and Zhai, Xiaohua},
  year={2025},
  journal={arXiv preprint arXiv:2502.14786}
}        

@article{zhai2023sigmoid,
  title={Sigmoid loss for language image pre-training},
  author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
  journal={arXiv preprint arXiv:2303.15343},
  year={2023}
}

@misc{big_vision,
  author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
  title = {Big Vision},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/google-research/big_vision}}
}