Vit Large Patch16 Siglip Gap 512.v2 Webli

🚀 Model card for vit_large_patch16_siglip_gap_512.v2_webli

A SigLIP 2 ViT (image encoder only) for timm, equivalent to the image tower from https://huggingface.co/timm/ViT-L-16-SigLIP2-512. The gap variant uses global average pooling and has the attention pooling head removed.

🚀 Quick Start

This is a SigLIP 2 ViT image encoder designed for timm. It can be used for image feature extraction tasks.

✨ Features

• Based on the SigLIP 2 architecture, suitable for multilingual vision - language tasks.
• The gap variant uses global average pooling, removing the attention pooling head.

📚 Documentation

Model Details

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}
        }
        

@inproceedings{zhai2023sigmoid,
          title={Sigmoid loss for language image pre-training},
          author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
          booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
          pages={11975--11986},
          year={2023}
        }
        

📄 License

This model is licensed under the Apache-2.0 license.