Hugging Face's logo

trtd56
/
practical_nlp_course_3

Text Classification
Transformers
Safetensors
distilbert
Inference Endpoints
Model card Files Community
trtd56 commited on
Commit
f0e32c0
•
1 Parent(s): 307de36

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +51 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +74 -0
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfafc8c0662d9c8f39621a64c74260f2ad120310c8dd24886de2dddaf599b4e
3
+ size 439391
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "auto_map": {
45
+ "AutoTokenizer": [
46
+ "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
47
+ null
48
+ ]
49
+ },
50
+ "bos_token": "[CLS]",
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_lower_case": true,
54
+ "do_subword_tokenize": true,
55
+ "do_word_tokenize": true,
56
+ "eos_token": "[SEP]",
57
+ "jumanpp_kwargs": null,
58
+ "keep_accents": true,
59
+ "mask_token": "[MASK]",
60
+ "mecab_kwargs": {
61
+ "mecab_dic": "unidic_lite"
62
+ },
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "never_split": null,
65
+ "pad_token": "<pad>",
66
+ "remove_space": true,
67
+ "sep_token": "[SEP]",
68
+ "subword_tokenizer_type": "sentencepiece",
69
+ "sudachi_kwargs": null,
70
+ "tokenize_chinese_chars": false,
71
+ "tokenizer_class": "BertJapaneseTokenizer",
72
+ "unk_token": "<unk>",
73
+ "word_tokenizer_type": "mecab"
74
+ }