Update README.md

README.md

@@ -1,3 +1,17 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- Elliott/Openr1-Math-46k-8192
+base_model:
+- open-r1/Qwen2.5-Math-7B-RoPE-300k
+- Qwen/Qwen2.5-Math-7B
+pipeline_tag: reinforcement-learning
+---
+
+# 📄 Introduction
+
+Supervised Reinforcement Fine-Tuning (SRFT) is a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms.
+
+Paper: [arXiv](https://arxiv.org/abs/2506.19767)
+
+Project Website: [SRFT](https://anonymous.4open.science/w/SRFT2025)