Add library_name, pipeline_tag and base_model metadata

This PR updates the `pipeline_tag` to be `image-text-to-text`, and adds the library name and base model metadata.

It would be great to update the other model repos too :)

Cheers

README.md

@@ -4,7 +4,10 @@ language:
 - en
 metrics:
 - accuracy
-pipeline_tag: text-generation
+pipeline_tag: image-text-to-text
+library_name: transformers
+base_model:
+- OpenGVLab/InternVL2-8B
 ---
 # MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning