Update app.py

app.py

@@ -27,7 +27,7 @@ def load_model():
         model_type = 'llama',
         max_new_tokens = 1096,
         temperature = 0.2,
-        repetition_penalty = 1.13,
+        repetition_penalty = 1.13
         # gpu_layers = 2
     )
     return llm