Add `pipeline_tag` and `library_name` to model card

This PR enhances the model card by adding two important metadata tags:
- `pipeline_tag: ROBOTICS`: Ensures the model is discoverable under the appropriate task category on the Hugging Face Hub, improving its visibility for users interested in robotics applications.
- `library_name: transformers`: Explicitly declares compatibility with the Hugging Face Transformers library, as evidenced by the `transformers_version` in `config.json` and the naming conventions in `config.json` and `preprocessor_config.json`. This will enable the interactive "how to use" widget on the model page, providing convenient code snippets for easier adoption.

These additions enhance the model's visibility and usability on the Hugging Face Hub.

README.md

@@ -1,11 +1,13 @@
 ---
-license: cc-by-nc-4.0
+base_model:
+- fnlp/RoboOmni
 datasets:
 - fnlp/OmniAction-LIBERO
 language:
 - en
-base_model:
-- fnlp/RoboOmni
+license: cc-by-nc-4.0
+pipeline_tag: ROBOTICS
+library_name: transformers
 ---
 
 <div align="center">
@@ -60,5 +62,4 @@ If you find our paper and code useful in your research, please cite our paper.
   archivePrefix={arXiv},
   primaryClass={cs.RO},
 }
-```
-
+```