update generate parameters

app.py

@@ -4,7 +4,8 @@ from transformers import BertTokenizer, BartForConditionalGeneration
 
 title = "HIT-TMG/dialogue-bart-large-chinese"
 description = """
-This is a seq2seq model fine-tuned on several Chinese dialogue datasets, from bart-large-chinese. \n
+This is a seq2seq model pre-trained on several Chinese dialogue datasets, from bart-large-chinese. 
+However it is just a simple demo for this pre-trained model. It's better to fine-tune it on downstream tasks for better performance \n
 See some details of model card at https://huggingface.co/HIT-TMG/dialogue-bart-large-chinese . \n\n
 Besides starting the conversation from scratch, you can also input the whole dialogue history utterance by utterance seperated by '[SEP]'. \n
 """