Add pipeline_tag, library_name and links to paper/code

Hi! I'm Niels from the Hugging Face community team.

I've opened this PR to enhance the model card with standardized metadata and prominent links. Specifically, I've:
- Added `pipeline_tag: text-generation` for better discoverability in the Hub's model gallery.
- Added `library_name: transformers` to enable the automated code snippet features.
- Added links to the research paper and the official GitHub repository in the introduction.

These changes make the model easier to find and use. Please review and merge if this looks good!

README.md

@@ -1,19 +1,23 @@
 ---
-license: apache-2.0
 base_model:
-  - IIGroup/X-Coder-SFT-Qwen2.5-7B
+- IIGroup/X-Coder-SFT-Qwen2.5-7B
 datasets:
-  - IIGroup/X-Coder-RL-40k
+- IIGroup/X-Coder-RL-40k
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - code
-  - rl
-  - competitive-programming
+- code
+- rl
+- competitive-programming
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 # X-Coder-RL-Qwen2.5-7B
 
+[**Paper**](https://huggingface.co/papers/2601.06953) | [**Code**](https://github.com/JieWu02/X-Coder)
+
 X-Coder-RL-Qwen2.5-7B is a strong code reasoning foundation model trained with RLVR on fully synthetic rl data, achieving strong reasoning performance on competitive programming.
 
 ## Model Description
@@ -80,4 +84,4 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## License
 
-This project is licensed under the Apache License 2.0.
+This project is licensed under the Apache License 2.0.