Update README.md

README.md

@@ -106,8 +106,6 @@ outputs = model.generate(tokenized_chat.to(model.device), max_new_tokens=2048)
 output_text = tokenizer.decode(outputs[0])
 ```
 
-We recommend using the following set of parameters for inference. Note that our model does not have the default system_prompt.
-
 ### Use with vLLM
 ```SHELL
 pip install vllm --upgrade
@@ -116,6 +114,8 @@ pip install vllm --upgrade
 ```SHELL
 vllm serve zhiqing/Hunyuan-MT-Chimera-7B-INT8
 ```
+
+We recommend using the following set of parameters for inference. Note that our model does not have the default system_prompt.
 ```json
 {
   "top_k": 20,