Add pipeline tag, library name, project page and MIT License

README.md

@@ -1,21 +1,25 @@
 ---
-license: apache-2.0
+license: mit
 tags:
 - Vision
 - Multi-model
 - 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-base
 
 [[Git-RSCLIP]](https://arxiv.org/pdf/2501.00895) is pre-trained on the Git-10M dataset (a global-scale remote sensing image-text pair dataset, consisting of 10 million image-text pairs) at size 256x256, first released in [this repository](https://github.com/chen-yang-liu/Text2Earth). It employs a similar structure to [[google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224)]. 
 
+Project page: https://chen-yang-liu.github.io/Text2Earth/
+Code: https://github.com/Chen-Yang-Liu/Text2Earth
+
 This is a **base version**, the **large version** is here: [[**Git-RSCLIP-large**](https://huggingface.co/lcybuaa/Git-RSCLIP)]
 
 ## Intended uses & limitations
@@ -101,4 +105,7 @@ Texts are tokenized and padded to the same length (64 tokens).
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2501.00895},
 }
-```
+```
+
+## License
+This repo is distributed under [MIT License](https://github.com/Chen-Yang-Liu/Change-Agent/blob/main/LICENSE.txt). The code can be used for academic purposes only.