Update app.py

app.py

@@ -49,6 +49,8 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         generated_text = None
         # Get the last message from the generated text
         generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    except Exception as e:
+            return f"Generation error: {e}"
         
     def extract_content_after_output(text):
         """
@@ -65,12 +67,11 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
             # If 'output' is not found, return an empty string
             return "Retry to get output, the model failed to generated required output(This occurs rarely🤷‍♂️)"
             
-            lines = extract_user_content(generated_text)
+    lines = extract_user_content(generated_text)
             
-            return lines
+    return lines
+        
         
-        except Exception as e:
-            return f"Generation error: {e}"
 
 demo = gr.ChatInterface(
     respond,