Update app.py

app.py

@@ -83,8 +83,8 @@ class DocumentRetrievalAndGeneration:
             device_map="auto",
             quantization_config=quantization_config,
             token=hf_token
-        )  quantization_config=quantization_config
-        
+            quantization_config=quantization_config
+        )
         return tokenizer, model
 
     def generate_response_with_timeout(self, input_ids, max_new_tokens=1000):