Add model card

This PR improves the model card by:
- Adding a `pipeline_tag`, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=image-text-to-text.
- Adding the `library_name`.
- Adding a link to the paper [ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter](https://huggingface.co/papers/2305.07490)
- Adding a link to the Github repository

README.md

@@ -1,3 +1,13 @@
+---
+license: bsd-3-clause
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
+# ArtGPT-4: Artistic Vision-Language Understanding with Adapter-enhanced MiniGPT-4
+
+This is a model card for the model described in the paper [ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter](https://huggingface.co/papers/2305.07490).
+
+See the code at https://github.com/DLYuanGod/ArtGPT-4.
 
 ## Getting Started
 ### Installation
@@ -68,4 +78,4 @@ We use [Laion-aesthetic](https://github.com/LAION-AI/laion-datasets/blob/main/la
 ## License
 This repository is under [BSD 3-Clause License](LICENSE.md).
 Many codes are based on [Lavis](https://github.com/salesforce/LAVIS) with 
-BSD 3-Clause License [here](LICENSE_Lavis.md).
+BSD 3-Clause License [here](LICENSE_Lavis.md).