helboukkouri commited on
Commit
fb2a60d
1 Parent(s): e23629c

update tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[BOW]": 258,
3
+ "[CLS]": 256,
4
+ "[EOW]": 259,
5
+ "[MASK]": 261,
6
+ "[PAD]": 260,
7
+ "[SEP]": 257
8
+ }
special_tokens_map.json CHANGED
@@ -1 +1,11 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[BOW]",
4
+ "[EOW]"
5
+ ],
6
+ "cls_token": "[CLS]",
7
+ "mask_token": "[MASK]",
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]"
10
+ }
11
+
tokenizer_config.json CHANGED
@@ -1,21 +1,70 @@
1
  {
2
- "name_or_path": "helboukkouri/character-bert",
3
- "tokenizer_class": "CharacterBertTokenizer",
4
- "max_word_length": 50,
5
- "do_lower_case": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "do_basic_tokenize": true,
7
- "bow_character_id": 258,
8
- "eow_character_id": 259,
9
- "pad_character_id": 260,
10
- "unk_token": "[UNK]",
11
- "sep_token": "[SEP]",
12
- "pad_token": "[PAD]",
13
  "cls_token": "[CLS]",
 
14
  "mask_token": "[MASK]",
15
- "auto_map": {
16
- "AutoTokenizer": [
17
- "tokenization_character_bert.CharacterBertTokenizer",
18
- null
19
- ]
20
- }
21
- }
 
 
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "256": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "257": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "258": {
20
+ "content": "[BOW]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "259": {
28
+ "content": "[EOW]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "260": {
36
+ "content": "[PAD]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "261": {
44
+ "content": "[MASK]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "additional_special_tokens": [
53
+ "[BOW]",
54
+ "[EOW]"
55
+ ],
56
+ "clean_up_tokenization_spaces": true,
57
  "do_basic_tokenize": true,
58
+ "do_lower_case": true,
 
 
 
 
 
59
  "cls_token": "[CLS]",
60
+ "sep_token": "[SEP]",
61
  "mask_token": "[MASK]",
62
+ "pad_token": "[PAD]",
63
+ "max_word_length": 50,
64
+ "model_max_length": 512,
65
+ "never_split": null,
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "CharacterBertTokenizer"
69
+ }
70
+