Add pipeline tag

This PR ensures the model is tagged with "image-text-to-text" just like other multimodal models like LLaVa.

README.md

@@ -1,3 +1,7 @@
+---
+pipeline_tag: image-text-to-text
+---
+
 # Model Card
 <!-- Provide a quick summary of what the model is/does. -->
 Parrot is a multi-language and multi-modal large language model capable of achieving excellent performance.
@@ -34,4 +38,4 @@ If you find Parrot useful, please cite the paper
 ```
 
 # License
-The project is licensed under Apache License Version 2.0 and is restricted to uses that comply with the license agreements of Qwen and Clip.
+The project is licensed under Apache License Version 2.0 and is restricted to uses that comply with the license agreements of Qwen and Clip.