Update README.md

README.md

@@ -106,7 +106,10 @@ output_text = tokenizer.decode(output_id[0][input_ids.shape[1] :])
 print(output_text)
 ```
 
-## curl Instructions
+## Running with vLLM
+```py
+vllm serve Writer/palmyra-mini-thinking-a
+```
 ```py
 curl -X POST http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
@@ -123,11 +126,6 @@ curl -X POST http://localhost:8000/v1/chat/completions \
   }'
 ```
 
-## VLLM Inference
-```py
-vllm serve Writer/palmyra-mini-thinking-a
-```
-
 
 ## Ethical Considerations