Add image-text-to-text pipeline tag

This PR adds the `image-text-to-text` pipeline tag to the model card metadata. This will improve discoverability of the model on the Hugging Face model hub. The model processes both image and text inputs to generate text outputs, making this tag appropriate.

README.md

@@ -1,7 +1,7 @@
 ---
-pipeline_tag: image-text-to-text
 library_name: transformers
 license: mit
+pipeline_tag: image-text-to-text
 ---
 
 # Skywork-R1V2
@@ -372,4 +372,4 @@ If you use Skywork-R1V in your research, please cite:
 }
 ```
 
-*This project is released under an open-source license.*
+*This project is released under an open-source license.*