Fix pipeline tag, add library name

This PR fixes the pipeline tag, so that it corresponds to a multimodal model rather than only the visual modality.
The correct pipeline tag is `image-text-to-text`. This ensures that the model can be found at https://huggingface.co/models?pipeline_tag=image-text-to-text&sort=trending.

It also adds the `library_name` to the metadata, which is `transformers` since it's compatible with the Transformers library.

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
 base_model:
 - google/siglip-so400m-patch14-384
-pipeline_tag: image-feature-extraction
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+
 # Model Card for CoMP-MM-1B
 
 <!-- Provide a quick summary of what the model is/does. -->