Hugging Face's logo

cahya
/
nusa-tokenizer

Transformers
Inference Endpoints
Model card Files Community
cahya commited on
Commit
ff9010d
·
verified ·
1 Parent(s): 989c7ab

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +37 -1
  2. tokenizer.json +47 -1
  3. tokenizer_config.json +48 -2
special_tokens_map.json CHANGED
@@ -1 +1,37 @@
1
- {}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json CHANGED
@@ -2,7 +2,53 @@
2
  "version": "1.0",
3
  "truncation": null,
4
  "padding": null,
5
- "added_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "normalizer": null,
7
  "pre_tokenizer": {
8
  "type": "Sequence",
 
2
  "version": "1.0",
3
  "truncation": null,
4
  "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 65000,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 65001,
17
+ "content": "[SEP]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 65002,
26
+ "content": "[PAD]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 65003,
35
+ "content": "[CLS]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 65004,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
  "normalizer": null,
53
  "pre_tokenizer": {
54
  "type": "Sequence",
tokenizer_config.json CHANGED
@@ -1,7 +1,53 @@
1
  {
2
- "added_tokens_decoder": {},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": false,
 
4
  "extra_special_tokens": {},
 
5
  "model_max_length": 1000000000000000019884624838656,
6
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
7
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "65000": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "65001": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65002": {
20
+ "content": "[PAD]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "65003": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "65004": {
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": false,
45
+ "cls_token": "[CLS]",
46
  "extra_special_tokens": {},
47
+ "mask_token": "[MASK]",
48
  "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "unk_token": "[UNK]"
53
  }