Update app.py

app.py

@@ -10,8 +10,10 @@ model = AutoModelForCausalLM.from_pretrained(
     dtype=torch.float16,
     device_map="auto"
 )
-
+def formatted_prompt(question)-> str:
+    return f"<|user|>\n{question}</s>\n<|assistant|>"
 def generate_response(prompt):
+    prompt = formatted_prompt
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
     generation_config = GenerationConfig(