HuyenNguyen commited on
Commit
3f5bee9
1 Parent(s): cf5865a

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +2 -2
  2. special_tokens_map.json +0 -16
  3. tokenizer_config.json +34 -0
  4. vocab.json +64 -66
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 92,
3
- "<s>": 91
4
  }
 
1
  {
2
+ "</s>": 90,
3
+ "<s>": 89
4
  }
special_tokens_map.json CHANGED
@@ -1,20 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "</s>",
12
- "lstrip": false,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
- ],
18
  "bos_token": "<s>",
19
  "eos_token": "</s>",
20
  "pad_token": "[PAD]",
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "[PAD]",
tokenizer_config.json CHANGED
@@ -1,4 +1,38 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "do_lower_case": false,
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "87": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "88": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "89": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "90": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": true,
38
  "do_lower_case": false,
vocab.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "vi": {
3
- "[PAD]": 90,
4
- "[UNK]": 89,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
@@ -27,69 +27,67 @@
27
  "|": 0,
28
  "à": 23,
29
  "á": 24,
30
- "â": 25,
31
- "ã": 26,
32
- "è": 27,
33
- "é": 28,
34
- "ê": 29,
35
- "ì": 30,
36
- "í": 31,
37
- "ò": 32,
38
- "ó": 33,
39
- "ô": 34,
40
- "õ": 35,
41
- "ù": 36,
42
- "ú": 37,
43
- "ý": 38,
44
- "ă": 39,
45
- "đ": 40,
46
- "ĩ": 41,
47
- "ũ": 42,
48
- "ơ": 43,
49
- "ư": 44,
50
- "": 45,
51
- "": 46,
52
- "": 47,
53
- "": 48,
54
- "": 49,
55
- "": 50,
56
- "": 51,
57
- "": 52,
58
- "": 53,
59
- "": 54,
60
- "": 55,
61
- "": 56,
62
- "": 57,
63
- "": 58,
64
- "": 59,
65
- "ế": 60,
66
- "": 61,
67
- "": 62,
68
- "": 63,
69
- "": 64,
70
- "": 65,
71
- "": 66,
72
- "": 67,
73
- "": 68,
74
- "": 69,
75
- "": 70,
76
- "": 71,
77
- "": 72,
78
- "": 73,
79
- "": 74,
80
- "": 75,
81
- "": 76,
82
- "": 77,
83
- "": 78,
84
- "": 79,
85
- "": 80,
86
- "": 81,
87
- "": 82,
88
- "": 83,
89
- "": 84,
90
- "": 85,
91
- "": 86,
92
- "ỷ": 87,
93
- "ỹ": 88
94
  }
95
  }
 
1
  {
2
  "vi": {
3
+ "[PAD]": 88,
4
+ "[UNK]": 87,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
 
27
  "|": 0,
28
  "à": 23,
29
  "á": 24,
30
+ "ã": 25,
31
+ "è": 26,
32
+ "é": 27,
33
+ "ê": 28,
34
+ "ì": 29,
35
+ "í": 30,
36
+ "ò": 31,
37
+ "ó": 32,
38
+ "õ": 33,
39
+ "ù": 34,
40
+ "ú": 35,
41
+ "ý": 36,
42
+ "ă": 37,
43
+ "đ": 38,
44
+ "ĩ": 39,
45
+ "ũ": 40,
46
+ "ơ": 41,
47
+ "ư": 42,
48
+ "": 43,
49
+ "": 44,
50
+ "": 45,
51
+ "": 46,
52
+ "": 47,
53
+ "": 48,
54
+ "": 49,
55
+ "": 50,
56
+ "": 51,
57
+ "": 52,
58
+ "": 53,
59
+ "": 54,
60
+ "": 55,
61
+ "": 56,
62
+ "": 57,
63
+ "ế": 58,
64
+ "": 59,
65
+ "": 60,
66
+ "": 61,
67
+ "": 62,
68
+ "": 63,
69
+ "": 64,
70
+ "": 65,
71
+ "": 66,
72
+ "": 67,
73
+ "": 68,
74
+ "": 69,
75
+ "": 70,
76
+ "": 71,
77
+ "": 72,
78
+ "": 73,
79
+ "": 74,
80
+ "": 75,
81
+ "": 76,
82
+ "": 77,
83
+ "": 78,
84
+ "": 79,
85
+ "": 80,
86
+ "": 81,
87
+ "": 82,
88
+ "": 83,
89
+ "": 84,
90
+ "": 85,
91
+ "": 86
 
 
92
  }
93
  }