Update app.py

app.py

@@ -44,6 +44,7 @@ def inference(message, history, systemPrompt=SYSTEM_PROMPT, temperature=0.9, max
     for stream_part in stream:
         partial_response += stream_part.token.text
         yield partial_response
+    return partial_response.stripsuffix("<|END_OF_TURN_TOKEN|>")
 
 
 myAdditionalInputs = [