Hugging Face's logo

cointegrated
/
bert-char-ctc-en-ru-translit-v0

Fill-Mask
Transformers
Safetensors
bert
Model card Files
xet
Community
cointegrated commited on
Commit
b4eed35
·
verified ·
1 Parent(s): ee388d7

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +65 -62
tokenizer_config.json CHANGED
@@ -1,62 +1,65 @@
1
- {
2
- "added_tokens_decoder": {
3
- "1": {
4
- "content": "[pad]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "2": {
12
- "content": "[unk]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "3": {
20
- "content": "[cls]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "5": {
28
- "content": "[mask]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "6": {
36
- "content": "[bos]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "7": {
44
- "content": "[eos]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- }
51
- },
52
- "bos_token": "[bos]",
53
- "clean_up_tokenization_spaces": true,
54
- "cls_token": "[cls]",
55
- "do_lower_case": false,
56
- "eos_token": "[eos]",
57
- "mask_token": "[mask]",
58
- "model_max_length": 1024,
59
- "pad_token": "[pad]",
60
- "tokenizer_class": "CharTokenizer",
61
- "unk_token": "[unk]"
62
- }
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "[pad]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "[unk]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[cls]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "5": {
28
+ "content": "[mask]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "6": {
36
+ "content": "[bos]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "7": {
44
+ "content": "[eos]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "[bos]",
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "[cls]",
55
+ "do_lower_case": false,
56
+ "eos_token": "[eos]",
57
+ "mask_token": "[mask]",
58
+ "model_max_length": 1024,
59
+ "pad_token": "[pad]",
60
+ "tokenizer_class": "CharTokenizer",
61
+ "unk_token": "[unk]",
62
+ "auto_map": {
63
+ "AutoTokenizer": ["char_tokenizer.CharTokenizer", null]
64
+ }
65
+ }