update readme

README.md

@@ -121,18 +121,23 @@ print(response)
 We list some instructions used in our SFT. You can use them to help you. You can use the other ways to prompt the model, but the following are recommended. InternLM2-Math may combine the following abilities but it is not guaranteed.
 
 Translate proof problem to Lean:
+
 ![nl2lean3](https://raw.githubusercontent.com/InternLM/InternLM-Math/main/assets/nl2lean.jpeg)
 
 Using Lean 3 to solve GSM8K problem:
+
 ![gsm8k_lean](https://raw.githubusercontent.com/InternLM/InternLM-Math/main/assets/gsm8k_lean.jpeg)
 
 Generate problem based on Lean 3 code:
+
 ![lean_problem](https://raw.githubusercontent.com/InternLM/InternLM-Math/main/assets/lean_problem.jpeg)
 
 Play 24 point game:
+
 ![24](https://raw.githubusercontent.com/InternLM/InternLM-Math/main/assets/24.jpeg)
 
 Augment a harder math problem:
+
 ![augment_hard](https://raw.githubusercontent.com/InternLM/InternLM-Math/main/assets/augment_hard.jpeg)
 
 | Description | Query |