Add pipeline tag and library name

This PR improves the model card by adding the `pipeline_tag`, `library_name`, and a link to the project page. The `pipeline_tag` is set to `image-feature-extraction` as this is the main functionality demonstrated in the usage examples. The `library_name` is set to `transformers`, as the model utilizes the Transformers library. Also corrected the year in bibtex citation.

README.md

@@ -6,10 +6,11 @@ tags:
 - Vision-Language
 - Remote-sensing
 widget:
-- src: >-
-    https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
   candidate_labels: playing music, playing sports
   example_title: Cat & Dog
+pipeline_tag: image-feature-extraction
+library_name: transformers
 ---
 
 # Git-RSCLIP
@@ -22,6 +23,7 @@ This is a **large version**, the **base version** is here: [[**Git-RSCLIP-base**
 
 You can use the raw model for tasks like zero-shot image classification and image-text retrieval.
 
+Project page: https://chen-yang-liu.github.io/Text2Earth/
 
 ### How to use
 
@@ -80,7 +82,7 @@ For more code examples, we refer to the [documentation](https://huggingface.co/t
 
 ### Training data
 
-Git-RSCLIP is pre-trained on the Git-10M dataset (a global-scale remote sensing image-text pair dataset, consisting of 10 million image-text pairs) [(Liu et al., 2024)](https://github.com/chen-yang-liu/Text2Earth).
+Git-RSCLIP is pre-trained on the Git-10M dataset (a global-scale remote sensing image-text pair dataset, consisting of 10 million image-text pairs) [(Liu et al., 2025)](https://github.com/chen-yang-liu/Text2Earth).
 
 ### Preprocessing