Add `library_name` and `pipeline_tag` metadata

This PR improves the model card by adding the `library_name` and `pipeline_tag` to the metadata.

* **`library_name: transformers`**: The model is compatible with the Hugging Face Transformers library, as demonstrated by the `Quickstart` code snippet provided in the README and the model's configuration files. This will enable the automated "how to use" widget on the model page.
* **`pipeline_tag: image-text-to-text`**: The model takes visual input (images/videos) and text queries to generate text responses, which aligns with the `image-text-to-text` pipeline. This will improve model discoverability on the Hub.

No changes are made to the content of the README as existing links and usage examples are already well-documented.

README.md

@@ -1,5 +1,7 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 
 # VST-3B-RL
@@ -149,4 +151,4 @@ If you find our work helpful, feel free to give us a cite.
   journal={arXiv preprint arXiv:2511.05491},
   year={2025}
 }
-```
+```