Add pipeline tag and library name to model card

This PR enhances the model card by adding key metadata tags:
- `pipeline_tag: text-generation`: This helps categorize the model for text generation tasks on the Hub, improving discoverability.
- `library_name: transformers`: This indicates compatibility with the Hugging Face Transformers library, which will enable an automated "How to use" code snippet on the model page for easy integration.

README.md

@@ -1,13 +1,16 @@
 ---
-license: mit
 base_model:
 - Qwen/Qwen3-30B-A3B-Thinking-2507
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 <div align="center">
 
 #  MarsRL
 <div>
-   Advancing <strong>M</strong>ulti-<strong>A</strong>gent <strong>R</strong>easoning <strong>S</strong>ystem via <strong>R</strong>einforcement <strong>L</strong>earning with Agentic Pipeline Parallelism
+   Advancing **M**ulti-**A**gent **R**easoning **S**ystem via **R**einforcement **L**earning with Agentic Pipeline Parallelism
 </div>
 <a href="https://arxiv.org/pdf/2511.11373" target="_blank">Paper</a> | <a href="https://github.com/liushulinle/MarsRL" target="_blank">GitHub</a>
 </div>