Update README.md

README.md

@@ -252,7 +252,7 @@ After launching a vLLM server, you can call the server with tool-call support us
     )
 
 >>> completion = client.chat.completions.create(
-      model="Llama-Nemotron-Nano-v1.1",
+      model="Llama-Nemotron-Nano-4B-v1.1",
       messages=[
         {"role": "system", "content": "detailed thinking on"},
         {"role": "user", "content": "My bill is $100. What will be the amount for 18% tip?"},