Update README.md

README.md

@@ -7,8 +7,6 @@ language:
 - en
 ---
 <h1 align="center">
-<img src="./assets/jiuzhang.png" width="100" alt="JiuZhang" />
-<br>
 JiuZhang3.0: Efficiently Improving Mathematical
 Reasoning by Training Small Data Synthesis Models
 </h1>
@@ -22,10 +20,7 @@ Reasoning by Training Small Data Synthesis Models
 ## Introduction
 JiuZhang3.0 is a series of fine-tuned models for math reasoning continually pre-trained on corpus synthesized by our carefully trained small LLM.
 
-### Method
-<img src="./assets/model.png" alt="JiuZhang3.0" />
-
-### Experimental Results
+## Experimental Results
 For more evaluation results, please refer to the [Paper](https://arxiv.org/abs/2405.14365)
 
 | Models                   | GSM8k | MATH | SVAMP | ASDiv | MAWPS | CARP | Avg.  |