Update app.py

app.py

@@ -48,7 +48,7 @@ def generate_response(message, max_tokens, temperature, top_p):
     global stop_signal
     stop_signal = False
 
-    prompt = f"{message}"
+    prompt = f"Contexto: {message}\nResposta curta e direta:"
     
     inputs = tokenizer(prompt, return_tensors="pt").to(device)