File size: 897 Bytes
3cc5b2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
---

language:

- zh

license:

- apache-2.0

---

```python

import jieba_fast

from transformers import BertTokenizer

from transformers import BigBirdModel

class JiebaTokenizer(BertTokenizer):

    def __init__(

        self, pre_tokenizer=lambda x: jieba_fast.cut(x, HMM=False), *args, **kwargs

    ):

        super().__init__(*args, **kwargs)

        self.pre_tokenizer = pre_tokenizer

    def _tokenize(self, text, *arg, **kwargs):

        split_tokens = []

        for text in self.pre_tokenizer(text):

            if text in self.vocab:

                split_tokens.append(text)

            else:

                split_tokens.extend(super()._tokenize(text))

        return split_tokens

model = BigBirdModel.from_pretrained('Lowin/chinese-bigbird-mini')

tokenizer = JiebaTokenizer.from_pretrained('Lowin/chinese-bigbird-mini')

```

https://github.com/LowinLi/chinese-bigbird