Hugging Face's logo

hotchpotch
/
japanese-splade-base-v1-dummy-fast-tokenizer-for-tei

PyTorch
Japanese
bert
Model card Files Community
japanese-splade-base-v1-dummy-fast-tokenizer-for-tei
File size: 1,397 Bytes 
7620bf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
56
57
58
59
60
61
62
63
64
 
{
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_lower_case": false,
  "do_subword_tokenize": true,
  "do_word_tokenize": true,
  "jumanpp_kwargs": null,
  "mask_token": "[MASK]",
  "mecab_kwargs": {
    "mecab_dic": "unidic_lite"
  },
  "model_max_length": 512,
  "never_split": null,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "subword_tokenizer_type": "wordpiece",
  "sudachi_kwargs": null,
  "tokenizer_class": "BertJapaneseTokenizer",
  "unk_token": "[UNK]",
  "word_tokenizer_type": "mecab"
}