Update README.md

README.md

@@ -101,9 +101,7 @@ Evaluation was conducted using the framework [lm-evaluation-harness](https://git
 
 ### Reproduction
 
-The results were obtained using the following commands:
-
-#### AIME2024
+The results were obtained using the following commands.
 ```
 # starting server
 python3 -m sglang.launch_server \
@@ -112,7 +110,10 @@ python3 -m sglang.launch_server \
     --trust-remote-code  \
     --n-share-experts-fusion 8 \
     --disable-radix-cache
+```
 
+#### AIME2024
+```
 # evaluating
 lm_eval --model local-completions \
     --model_args model=amd/DeepSeek-R1-MXFP4,base_url=http://localhost:30000/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=32000,temperature=0.6,top_p=0.95 \