Add relevant metadata, link to code and paper

This PR adds the `library_name` and `pipeline_tag` for this model card, so that it can be found using the filters on the hub.
It also links the model to the corresponding Github repository and paper page.

README.md

@@ -1,8 +1,13 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
 # <img src="assets/icon.png" width="35" /> ReFocus
 
 This repo contains the model for the paper "ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding"
 
-[**🌐 Homepage**](https://zeyofu.github.io/ReFocus/) |[**📑 Paper**](https://arxiv.org/abs/2501.05452) |  [**🔗 Code**](https://github.com/zeyofu/ReFocus_Code)
+[**🌐 Homepage**](https://zeyofu.github.io/ReFocus/) |[**📑 Paper**](https://huggingface.co/papers/2501.05452) |  [**🔗 Code**](https://github.com/zeyofu/ReFocus_Code)
 
 
 # Introduction
@@ -22,8 +27,4 @@ This model is finetuned based on Phi-3.5-vision, and we used the following promp
 To enforce the model to generate bounding box coordinates to refocus, you could try this prompt:
 ```
 <|image_1|>\n{question}\nThought: The areas to focus on in the image have bounding box coordinates:
-```
-
----
-license: apache-2.0
----
+```