temporary0-0name commited on
Commit
b707076
1 Parent(s): 148b761

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer_config.json +42 -0
special_tokens_map.json CHANGED
@@ -1,7 +1,13 @@
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": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "sep_token": "[SEP]",
12
  "unk_token": "[UNK]"
13
  }
tokenizer_config.json CHANGED
@@ -1,4 +1,46 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_lower_case": true,
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,