Update app.py

app.py

@@ -19,7 +19,8 @@ model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 
 def generate_answer(question):
-    inputs = tokenizer.encode("Question: " + question, return_tensors="pt")
+    inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+    #inputs = tokenizer.encode(question, return_tensors="pt")
     outputs = model.generate(inputs, max_length=2000, num_return_sequences=1, do_sample=True)
     answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return answer