Add `library_name` and update paper link, and remove redundant license section

This PR improves the model card by:
- Adding `library_name: transformers` to the metadata, enabling the "how to use" widget on the Hugging Face Hub, as indicated by the model's `config.json` and tokenizer configurations.
- Updating the placeholder paper link in the "Resources" section to the correct Hugging Face paper page: [VideoNSA: Native Sparse Attention Scales Video Understanding](https://huggingface.co/papers/2510.02295).
- Removing the redundant "

README.md

@@ -2,13 +2,14 @@
 language:
 - en
 license: apache-2.0
+pipeline_tag: video-text-to-text
 tags:
 - video-understanding
 - sparse-attention
 - vision-language
 - qwen2.5-vl
 - multimodal
-pipeline_tag: video-text-to-text
+library_name: transformers
 ---
 
 # VideoNSA: Native Sparse Attention for Video Understanding
@@ -75,10 +76,6 @@ For installation, training, and evaluation instructions, please refer to:
 
 ## Resources
 
-- 📄 [Paper](https://arxiv.org/abs/TODO)
+- 📄 [Paper](https://huggingface.co/papers/2510.02295)
 - 🌐 [Project Page](https://enxinsong.com/VideoNSA-web/)
-- 💻 [GitHub Repository](https://github.com/Espere-1119-Song/VideoNSA)
-
-## License
-
-This model is released under the Apache 2.0 License.
+- 💻 [GitHub Repository](https://github.com/Espere-1119-Song/VideoNSA)