RaduGabriel commited on
Commit
6d46779
·
verified ·
1 Parent(s): e64bb12

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +0 -16
  2. tokenizer.json +16 -20
  3. tokenizer_config.json +0 -20
special_tokens_map.json CHANGED
@@ -1,20 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "[SUBJ]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "[OBJ]",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
- ],
18
  "cls_token": "[CLS]",
19
  "mask_token": "[MASK]",
20
  "pad_token": "[PAD]",
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "cls_token": "[CLS]",
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
@@ -47,24 +61,6 @@
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
50
- },
51
- {
52
- "id": 28996,
53
- "content": "[SUBJ]",
54
- "single_word": false,
55
- "lstrip": false,
56
- "rstrip": false,
57
- "normalized": false,
58
- "special": true
59
- },
60
- {
61
- "id": 28997,
62
- "content": "[OBJ]",
63
- "single_word": false,
64
- "lstrip": false,
65
- "rstrip": false,
66
- "normalized": false,
67
- "special": true
68
  }
69
  ],
70
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
61
  "rstrip": false,
62
  "normalized": false,
63
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  }
65
  ],
66
  "normalizer": {
tokenizer_config.json CHANGED
@@ -39,28 +39,8 @@
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
- },
43
- "28996": {
44
- "content": "[SUBJ]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "28997": {
52
- "content": "[OBJ]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
  }
59
  },
60
- "additional_special_tokens": [
61
- "[SUBJ]",
62
- "[OBJ]"
63
- ],
64
  "clean_up_tokenization_spaces": true,
65
  "cls_token": "[CLS]",
66
  "do_basic_tokenize": true,
 
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
 
 
 
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,