Improve model card: Add pipeline tag and GitHub link

This PR updates the model card for the paper "On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models".

It adds the `pipeline_tag: text-generation` to the metadata, which helps with discoverability and categorization on the Hugging Face Hub. It also includes an explicit link to the GitHub repository for easy access to the project's code.

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+pipeline_tag: text-generation
 ---
 
 <h1 align="center">
@@ -26,6 +27,8 @@ Carnegie Mellon University, Language Technologies Institute
 
 This repository contains post-training related checkpoints in extrapolation tasks.
 
+**Code:** [GitHub Repository](https://github.com/Interplay-LM-Reasoning/Interplay-LM-Reasoning)
+
 ## 📚 Citation
 
 If you find this work or code useful, please consider citing: