ModelPrésentéExterne

Vit Base Patch16 Siglip Gap 384.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.

Sourcehuggingface.co/timm/vit_base_patch16_siglip_gap_384.v2_webli/tree/38ceeaccc91c9ad79ce5a8164f419f14a60f146a

TypeOtherVersionRevision 38ceeac

Source du modèle

Type: Other
Taille du fichier: 328 MB
Version: vRevision 38ceeac
Mis à jour: 27 sept. 2026
Téléchargements: 82
Source: Hugging Face

Description de la source

Model card for vit_base_patch16_siglip_gap_384.v2_webli

A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from https://huggingface.co/timm/ViT-B-16-SigLIP2-384. 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}
        }

Sources

1 source

Hugging FacePrincipalVersion 38ceeaccc91c9ad79ce5a8164f419f14a60f146a

huggingface.co/timm/vit_base_patch16_siglip_gap_384.v2_webli/tree/38ceeaccc91c9ad79ce5a8164f419f14a60f146a

Vérifié 27 sept.

Artefacts du modèle

2 artefacts

model.safetensors

safetensors · 328 MB · SHA-256 a6a5e666e5b2…cba7 · Hugging Face

Télécharger

pytorch_model.bin

bin · 328 MB · SHA-256 0120e2f82b96…232a · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme27 sept.huggingface.co/timm/vit_base_patch16_siglip_gap_384.v2_webli

--- tags: - timm - transformers - image-feature-extraction - siglip - siglip2 library_name: timm license: apache-2.0 datasets: - webli --- # Model card for vit_base_patch16_siglip_gap_384.v2_webli A SigLIP 2 ViT (image encoder only) for `timm`. Equivalent to image tower from https://huggingface.co/timm/ViT-B-16-SigLIP2-384. 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} } ```

Note27 sept.huggingface.co/timm/vit_base_patch16_siglip_gap_384.v2_webli

Source context: 82 downloads · 0 likes · Pipeline image-feature-extraction · Library timm · Repo timm/vit_base_patch16_siglip_gap_384.v2_webli