Vit So400m Patch14 Siglip Gap 378.v2 Webli
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from This gap variant uses global average pooling and has the attention pooling head removed.
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 1,54 GB
- Versão
- vRevision 7245d05
- Atualizado
- 27 de set. de 2026
- Downloads
- 69
- Fonte
- Hugging Face
Descrição da fonte
Model card for vit_so400m_patch14_siglip_gap_378.v2_webli
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from https://huggingface.co/timm/ViT-SO400M-14-SigLIP2-378. This gap variant uses global average pooling and has the attention pooling head removed.
Model Details
- 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
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}
}
Fontes
1 fonte
Fontes
1 fonteVerificado 27 de set.
Download files
Artefatos de modelo
2 artefatos
Artefatos de modelo
2 artefatosTrechos de fonte
2 trechos
Trechos de fonte
2 trechos--- tags: - timm - transformers - image-feature-extraction - siglip - siglip2 library_name: timm license: apache-2.0 datasets: - webli --- # Model card for vit_so400m_patch14_siglip_gap_378.v2_webli A SigLIP 2 ViT (image encoder only) for `timm`. Equivalent to image tower from https://huggingface.co/timm/ViT-SO400M-14-SigLIP2-378. This `gap` variant uses global average pooling and has the attention pooling head removed. ## Model Details - **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 ## Citation ```bibtex @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} } ``` ```bibtex @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} } ```
Source context: 69 downloads · 0 likes · Pipeline image-feature-extraction · Library timm · Repo timm/vit_so400m_patch14_siglip_gap_378.v2_webli
