Hugging Face's logo

nono1224
/
b3comp-twbert-1

Text Classification
Transformers
Safetensors
luke
Model card Files
xet
Community
nono1224 commited on
Commit
9d15763
·
verified ·
1 Parent(s): 4a5628e

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +34 -8
  2. tokenizer_config.json +55 -18
special_tokens_map.json CHANGED
@@ -1,15 +1,41 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
 
 
 
 
 
 
 
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "[URL]",
4
+ "[USER]"
5
+ ],
6
+ "cls_token": {
7
+ "content": "[CLS]",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
  "mask_token": {
14
+ "content": "[MASK]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false
26
  },
27
+ "sep_token": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "[UNK]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
  }
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,31 +25,68 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
42
  }
43
  },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": false,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "mask_token": "<mask>",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "pad_token": "<pad>",
51
- "sep_token": "</s>",
52
- "sp_model_kwargs": {},
53
- "tokenizer_class": "XLMRobertaTokenizer",
54
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[SEP]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[PAD]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[URL]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[USER]",
53
+ "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
+ },
59
+ "31999": {
60
+ "content": "\n",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
  }
67
  },
68
+ "additional_special_tokens": [
69
+ "[URL]",
70
+ "[USER]"
71
+ ],
72
+ "clean_up_tokenization_spaces": true,
73
+ "cls_token": "[CLS]",
74
+ "do_lower_case": false,
75
+ "do_subword_tokenize": true,
76
+ "do_word_tokenize": true,
77
+ "jumanpp_kwargs": null,
78
+ "keep_newlines": true,
79
+ "mask_token": "[MASK]",
80
+ "mecab_kwargs": {
81
+ "mecab_dic": "unidic_lite"
82
+ },
83
+ "model_max_length": 512,
84
+ "never_split": null,
85
+ "pad_token": "[PAD]",
86
+ "sep_token": "[SEP]",
87
+ "subword_tokenizer_type": "wordpiece",
88
+ "sudachi_kwargs": null,
89
+ "tokenizer_class": "BertJapaneseTokenizer",
90
+ "unk_token": "[UNK]",
91
+ "word_tokenizer_type": "mecab"
92
  }