Set pipeline tag to image-to-text and add project page link

This PR sets the pipeline tag to `image-to-text` and adds a link to the project page. The SigLIP 2 model can be used for generating text descriptions from images, as well as zero-shot image classification and image-text retrieval.

README.md

@@ -1,14 +1,13 @@
 ---
+library_name: transformers
 license: apache-2.0
+pipeline_tag: image-to-text
 tags:
 - vision
 widget:
-  - src: >-
-      https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg
-    candidate_labels: bee in the sky, bee on the flower
-    example_title: Bee
-library_name: transformers
-pipeline_tag: zero-shot-image-classification
+- src: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg
+  candidate_labels: bee in the sky, bee on the flower
+  example_title: Bee
 ---
 
 # SigLIP 2 Base
@@ -17,6 +16,8 @@ pipeline_tag: zero-shot-image-classification
 [SigLIP](https://huggingface.co/papers/2303.15343) with prior, independently developed techniques
 into a unified recipe, for improved semantic understanding, localization, and dense features.
 
+Project page: [https://github.com/google-research/big_vision](https://github.com/google-research/big_vision)
+
 ## Intended uses
 
 You can use the raw model for tasks like zero-shot image classification and
@@ -99,4 +100,4 @@ Evaluation of SigLIP 2 is shown below (taken from the paper).
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2502.14786}, 
 }
-```
+```