Add pipeline tag and link to project page

This PR adds the `image-text-to-text` pipeline tag to the model card, and adds a link to the project page. This ensures the model can be found when querying for image-text-to-text models.

README.md

@@ -1,11 +1,13 @@
 ---
-license: cc-by-4.0
 datasets:
 - UCSC-VLAA/Recap-DataComp-1B
 - mlfoundations/datacomp_1b
 library_name: open_clip
+license: cc-by-4.0
+pipeline_tag: image-text-to-text
 ---
-[[Paper]](https://arxiv.org/abs/2501.09446) [[github]](https://github.com/zw615/Double_Visual_Defense)
+
+[[Paper]](https://arxiv.org/abs/2501.09446) [[github]](https://github.com/zw615/Double_Visual_Defense) [[Project Page]](https://doublevisualdefense.github.io/)
 
 A DeltaCLIP-H/14-336 Model that is adversarially pre-trained with web-scale image-text data to reach non-robust-VLM helpfulness levels on clean data while being robust on adversarially attacked data.