Improve model card with metadata and links

This PR adds missing metadata to the model card, including the `library_name` and `pipeline_tag`. It also adds links to the paper and a description of the model based on the paper abstract.

README.md

@@ -1,3 +1,11 @@
----
-license: mit
----
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+This repository contains the R1-Code-Interpreter models described in [R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning](https://huggingface.co/papers/2505.21668).
+
+The models are fine-tuned Qwen-2.5 models (3B/7B/14B) trained using supervised fine-tuning (SFT) and reinforcement learning (RL) to generate code during step-by-step reasoning.
+
+For code and further details, please refer to the [Github repository](https://github.com/yongchao98/R1-Code-Interpreter) and the [project page](https://huggingface.co/yongchao98).