xaviergillard commited on
Commit
9baec12
1 Parent(s): e393d50

Upload tokenizer

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +9 -9
  3. vocab.txt +0 -0
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,38 +1,38 @@
1
  {
2
  "added_tokens_decoder": {
3
- "24309": {
4
- "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "24310": {
12
- "content": "[SEP]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "24311": {
20
- "content": "[PAD]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "24312": {
28
- "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "24313": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
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": false,
38
  "normalized": false,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff