Add model

README.md

@@ -23,6 +23,15 @@ A SigLIP 2 ViT (image encoder only) for `timm`. Equivalent to image tower from h
 
 ## 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},
@@ -32,12 +41,3 @@ A SigLIP 2 ViT (image encoder only) for `timm`. Equivalent to image tower from h
         }
         
 ```
-```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}
-        }
-        
-```