Add image-to-text pipeline tag and link to code

This PR improves the model card by setting the appropriate `pipeline_tag` as well as adding a link to the code.

README.md

@@ -1,22 +1,23 @@
 ---
+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 Large
 
-[SigLIP 2](https://huggingface.co/papers/2502.14786) extends the pretraining objective of
+[SigLIP 2](https://hf.co/papers/2502.14786) extends the pretraining objective of
 [SigLIP](https://huggingface.co/papers/2303.15343) with prior, independently developed techniques
 into a unified recipe, for improved semantic understanding, localization, and dense features.
 
+Code: https://github.com/google-research/big_vision
+
 ## Intended uses
 
 You can use the raw model for tasks like zero-shot image classification and
@@ -83,9 +84,7 @@ The model was trained on up to 2048 TPU-v5e chips.
 
 ## Evaluation results
 
-Evaluation of SigLIP 2 is shown below (taken from the paper).
-
-![Evaluation Table](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/sg2-blog/eval_table.png)
+Evaluation of SigLIP 2 is shown below (taken from the paper).\n\n![Evaluation Table](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/sg2-blog/eval_table.png)
 
 ### BibTeX entry and citation info
 
@@ -99,4 +98,4 @@ Evaluation of SigLIP 2 is shown below (taken from the paper).
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2502.14786}, 
 }
-```
+```