Improve model card: Add pipeline tag, relevant tags, paper and code links

This PR enhances the model card by:
- Adding `pipeline_tag: text-generation` to improve discoverability on the Hugging Face Hub.
- Adding `math` and `mathematical-reasoning` tags to categorize the model more accurately.
- Adding a direct link to the Hugging Face paper page ([DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning](https://huggingface.co/papers/2511.22570)) for easy access.
- Adding a direct link to this model's GitHub repository ([https://github.com/deepseek-ai/DeepSeek-Math-V2](https://github.com/deepseek-ai/DeepSeek-Math-V2)).

Please review and merge if these improvements are satisfactory.

README.md

@@ -1,8 +1,12 @@
 ---
-license: apache-2.0
-library_name: transformers
 base_model:
-  - deepseek-ai/DeepSeek-Math-V2
+- deepseek-ai/DeepSeek-Math-V2
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- math
+- mathematical-reasoning
 ---
 
 <!-- markdownlint-disable first-line-h1 -->
@@ -35,6 +39,8 @@ base_model:
 </div>
 
 # DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
+Paper: [DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning](https://huggingface.co/papers/2511.22570)
+Code: [https://github.com/deepseek-ai/DeepSeek-Math-V2](https://github.com/deepseek-ai/DeepSeek-Math-V2)
 
 ## 1. Introduction
 
@@ -90,4 +96,4 @@ This repository and the model weights are licensed under [the Apache License, Ve
 
 ## 8. Contact
 
-If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
+If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).