debug

main.py

@@ -13,13 +13,13 @@ app = FastAPI()
 @app.get("/llm_inference")
 def read_root(
         prompt: str,
-        model: str = "meta-llama/Llama-2-7b-chat-hf",
+        model: str = "mistralai/Mistral-7B-v0.1",
         temperature: float = 0.,
         max_tokens: int = 1024) -> List:
     sampling_params = SamplingParams(temperature=temperature, max_tokens=max_tokens)
 
     llm = LLM(model=model)
 
-    response = llm.generate([prompt], sampling_params, token=token)
+    response = llm.generate([prompt], sampling_params)
 
     return response