Update app.py

app.py

@@ -30,7 +30,7 @@ def initialize_llm(hf_token):
         tokenizer_name = model_name,
         context_window=3900,
         # model_kwargs={"token": hf_token, "quantization_config": quantization_config},
-        model_kwargs={"token": hf_token}
+        model_kwargs={"token": hf_token},
         tokenizer_kwargs={"token": hf_token},
         max_new_tokens=400,
         device_map="auto",