debug

main.py

@@ -13,7 +13,7 @@ app = FastAPI()
 @app.get("/llm_inference")
 def read_root(
         prompt: str,
-        model: str = "meta-llama/Llama-2-7b-hf",
+        model: str = "meta-llama/Llama-2-7b-chat-hf",
         temperature: float = 0.,
         max_tokens: int = 1024) -> List:
     sampling_params = SamplingParams(temperature=temperature, max_tokens=max_tokens)