Update app.py

app.py

@@ -9,7 +9,7 @@ system_message = "Eres un asistente que siempre responde en español."
 def load_llm():
     llm = AutoModelForCausalLM.from_pretrained(
         model_name="TheBloke/Llama-2-7B-Chat-GGUF",
-        model_file='llama-2-7b-chat.Q5_K_M.gguf'
+        model_file='llama-2-7b-chat.Q5_K_M.gguf',
         model_type='llama',
         max_new_tokens=2048,
         context_length = 4096,