Update README.md

README.md

@@ -1,9 +1,3 @@
-GPG: A Simple and Strong Reinforcement Learning
-Baseline for Model Reasoning
-https://arxiv.org/abs/2504.02546
-
-The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.
-
 ---
 license: apache-2.0
 datasets:
@@ -14,4 +8,9 @@ metrics:
 - accuracy
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
----
+---
+GPG: A Simple and Strong Reinforcement Learning
+Baseline for Model Reasoning
+https://arxiv.org/abs/2504.02546
+
+The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.