Update README.md

README.md

@@ -16,7 +16,7 @@ This model is a reinforcement learning fine-tuned version of **Qwen3-8B-Base**,
 - **Base Model**: Qwen3-8B-Base  
 - **Training Method**: Reinforcement Learning (DAPO)  
 - **Dataset**: DAPO-Math-17k  
-- **Checkpoint**: global_step_0(no RL training, i.e. Qwen3-8B-Base)
+- **Checkpoint**: global_step_0 (no RL training, i.e. Qwen3-8B-Base)
 
 ---