Update main.py

main.py

@@ -23,7 +23,7 @@ app = FastAPI()
 @app.post("/generate_response")
 async def generate_response(item: Validation):
     # Construct the complete prompt using the given system and user prompts
-    prompt = f"<s>[INST] <<SYS>> \n {item.system_prompt}<</SYS>> \n {item.user_prompt} [/INST]"
+    prompt = f"{item.user_prompt}"
     
     # Call the Llama model to generate a response
     output = llm(prompt, max_tokens=1024, stop=["Q:", "\n"], echo=True)  # Update parameters as needed