YanshekWoo
commited on
Commit
•
85e7694
1
Parent(s):
d012232
Update README.md
Browse files
README.md
CHANGED
@@ -18,9 +18,15 @@ We utilize 4 Chinese dialogue datasets from [LUGE](https://www.luge.ai/#/)
|
|
18 |
|
19 |
# Example
|
20 |
```python
|
21 |
-
#!/usr/bin/env python3
|
22 |
from transformers import BertTokenizer, BartForConditionalGeneration
|
23 |
|
|
|
24 |
tokenizer = BertTokenizer.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
|
25 |
model = BartForConditionalGeneration.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
```
|
|
|
18 |
|
19 |
# Example
|
20 |
```python
|
|
|
21 |
from transformers import BertTokenizer, BartForConditionalGeneration
|
22 |
|
23 |
+
# Note that tokenizer is an object of BertTokenizer, instead of BartTokenizer
|
24 |
tokenizer = BertTokenizer.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
|
25 |
model = BartForConditionalGeneration.from_pretrained("HIT-TMG/dialogue-bart-large-chinese")
|
26 |
+
|
27 |
+
# an example from CPC dev data
|
28 |
+
dialogue_history = "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 。"
|
29 |
+
input_ids = tokenizer(dialogue_history, return_tensors='pt').input_ids
|
30 |
+
output_ids = model.generate(input_ids)[0]
|
31 |
+
print(tokenizer.decode(output_ids))
|
32 |
```
|