Change pipeline tag to any-to-any

This PR changes the pipeline tag from `visual-question-answering` to the more appropriate `any-to-any` tag, since the model can perform a variety of tasks (not just VQA).

README.md

@@ -15,13 +15,12 @@ language:
 - en
 metrics:
 - accuracy
-pipeline_tag: visual-question-answering
+pipeline_tag: any-to-any
 base_model:
 - Qwen/Qwen2.5-1.5B-Instruct
 - DAMO-NLP-SG/VideoLLaMA3-2B-Image
 ---
 
-
 <p align="center">
     <img src="https://cdn-uploads.huggingface.co/production/uploads/626938b16f8f86ad21deb989/tt5KYnAUmQlHtfB1-Zisl.png" width="150" style="margin-bottom: 0.2;"/>
 <p>