YanshekWoo commited on
Commit
cdbedd8
1 Parent(s): e2a77ad

ADD examples

Browse files
Files changed (1) hide show
  1. app.py +3 -2
app.py CHANGED
@@ -4,10 +4,10 @@ from transformers import BertTokenizer, BartForConditionalGeneration
4
 
5
  title = "HIT-TMG/dialogue-bart-large-chinese-DuSinc"
6
  description = """
7
- This is a fine-tuned version of HIT-TMG/dialogue-bart-large-chinese on the DuSinc dataset. \n
 
8
  See some details of model card at https://huggingface.co/HIT-TMG/dialogue-bart-large-chinese-DuSinc . \n\n
9
  Besides starting the conversation from scratch, you can also input the whole dialogue history utterance by utterance seperated by '[SEP]'. \n
10
- (e.g. "可以认识一下吗[SEP]当然可以啦,你好。[SEP]嘿嘿你好,请问你最近在忙什么呢?[SEP]我最近养了一只狗狗,我在训练它呢。") \n
11
  """
12
 
13
 
@@ -18,6 +18,7 @@ tokenizer.truncation_side = 'left'
18
  max_length = 512
19
 
20
  examples = [
 
21
  ["你好。[SEP]嘿嘿你好,请问你最近在忙什么呢?[SEP]我最近养了一只狗狗,我在训练它呢。"]
22
  ]
23
 
 
4
 
5
  title = "HIT-TMG/dialogue-bart-large-chinese-DuSinc"
6
  description = """
7
+ This is a fine-tuned version of HIT-TMG/dialogue-bart-large-chinese on the DuSinc dataset.
8
+ But it only has chit-chat ability without knowledge since we haven't introduced knowledge retrieval interface yet.\n
9
  See some details of model card at https://huggingface.co/HIT-TMG/dialogue-bart-large-chinese-DuSinc . \n\n
10
  Besides starting the conversation from scratch, you can also input the whole dialogue history utterance by utterance seperated by '[SEP]'. \n
 
11
  """
12
 
13
 
 
18
  max_length = 512
19
 
20
  examples = [
21
+ ["你有什么爱好吗"],
22
  ["你好。[SEP]嘿嘿你好,请问你最近在忙什么呢?[SEP]我最近养了一只狗狗,我在训练它呢。"]
23
  ]
24