Hugging Face's logo

Noboru-Ta
/
bert-base-japanese-v3-wrime-sentiment

Text Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
Noboru-Ta commited on
Commit
178b54b
•
1 Parent(s): 29c63b3

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -7
  2. tokenizer_config.json +63 -63
  3. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json CHANGED
@@ -1,63 +1,63 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
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
- },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
- "do_subword_tokenize": true,
48
- "do_word_tokenize": true,
49
- "jumanpp_kwargs": null,
50
- "mask_token": "[MASK]",
51
- "mecab_kwargs": {
52
- "mecab_dic": "unidic_lite"
53
- },
54
- "model_max_length": 512,
55
- "never_split": null,
56
- "pad_token": "[PAD]",
57
- "sep_token": "[SEP]",
58
- "subword_tokenizer_type": "wordpiece",
59
- "sudachi_kwargs": null,
60
- "tokenizer_class": "BertJapaneseTokenizer",
61
- "unk_token": "[UNK]",
62
- "word_tokenizer_type": "mecab"
63
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "do_subword_tokenize": true,
48
+ "do_word_tokenize": true,
49
+ "jumanpp_kwargs": null,
50
+ "mask_token": "[MASK]",
51
+ "mecab_kwargs": {
52
+ "mecab_dic": "unidic_lite"
53
+ },
54
+ "model_max_length": 512,
55
+ "never_split": null,
56
+ "pad_token": "[PAD]",
57
+ "sep_token": "[SEP]",
58
+ "subword_tokenizer_type": "wordpiece",
59
+ "sudachi_kwargs": null,
60
+ "tokenizer_class": "BertJapaneseTokenizer",
61
+ "unk_token": "[UNK]",
62
+ "word_tokenizer_type": "mecab"
63
+ }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff