style change for readme

README.md

@@ -38,12 +38,12 @@ Sail-VL benefits from high-quality data and carefully curated training recipes.
 
 SAIL-VL not only outperforms the Qwen2-VL and InternVL2 series of models of comparable size, but is also competitive compared with recently released SoTAs, Aquila and InternVL-2.5.
 
-Performace Overview:
+### Performace Overview:
 ![lidar_map](statics/performance.png)
 The result is evaluated by our team with a VLMEvalKit variant.
 
 
-Detail Evaluations:
+### Detail Evaluations:
 
 | Benchmark                | InternVL-2 | Qwen2-VL | Aquila-VL-2B | InternVL-2.5 | **SAIL-VL-2B** |
 | --------------------- | ---------- | -------- | --------- | ------------ | -------------- |
@@ -96,6 +96,7 @@ Requirements:
 pip3 install einops transformers timm
 ```
 
+Code:
 
 ```Python
 import numpy as np