Hugging Face's logo

LoneWolfgang
/
bert-for-japanese-twitter-sentiment

Text Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
LoneWolfgang commited on
Commit
c992b48
•
1 Parent(s): 54dca2f

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +3 -0
  2. special_tokens_map.json +41 -0
  3. tokenizer_config.json +92 -0
  4. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "\n": 31999
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[PAD]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": 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
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff