roviso commited on
Commit
77acd54
1 Parent(s): d57bbae

Upload tokenizer

Browse files
Files changed (2) hide show
  1. added_tokens.json +2 -2
  2. vocab.json +143 -173
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 177,
3
- "<s>": 176
4
  }
 
1
  {
2
+ "</s>": 147,
3
+ "<s>": 146
4
  }
vocab.json CHANGED
@@ -3,179 +3,149 @@
3
  "\n": 0,
4
  "!": 2,
5
  "\"": 3,
6
- "#": 4,
7
- "$": 5,
8
- "%": 6,
9
- "&": 7,
10
- "'": 8,
11
- "(": 9,
12
- ")": 10,
13
- "+": 11,
14
- ",": 12,
15
- "-": 13,
16
- ".": 14,
17
- "/": 15,
18
- "0": 16,
19
- "1": 17,
20
- "2": 18,
21
- "3": 19,
22
- "4": 20,
23
- "5": 21,
24
- "6": 22,
25
- "7": 23,
26
- "8": 24,
27
- "9": 25,
28
- ":": 26,
29
- ";": 27,
30
- "=": 28,
31
- "?": 29,
32
- "A": 30,
33
- "B": 31,
34
- "C": 32,
35
- "D": 33,
36
- "E": 34,
37
- "F": 35,
38
- "G": 36,
39
- "H": 37,
40
- "I": 38,
41
- "J": 39,
42
- "K": 40,
43
- "L": 41,
44
- "M": 42,
45
- "N": 43,
46
- "O": 44,
47
- "P": 45,
48
- "Q": 46,
49
- "R": 47,
50
- "S": 48,
51
- "T": 49,
52
- "U": 50,
53
- "V": 51,
54
- "W": 52,
55
- "Y": 53,
56
- "Z": 54,
57
- "[": 55,
58
- "[PAD]": 176,
59
- "[UNK]": 175,
60
- "]": 56,
61
- "_": 57,
62
- "`": 58,
63
- "a": 59,
64
- "b": 60,
65
- "c": 61,
66
- "d": 62,
67
- "e": 63,
68
- "f": 64,
69
- "g": 65,
70
- "h": 66,
71
- "i": 67,
72
- "j": 68,
73
- "k": 69,
74
- "l": 70,
75
- "m": 71,
76
- "n": 72,
77
- "o": 73,
78
- "p": 74,
79
- "q": 75,
80
- "r": 76,
81
- "s": 77,
82
- "t": 78,
83
- "u": 79,
84
- "v": 80,
85
- "w": 81,
86
- "x": 82,
87
- "y": 83,
88
- "z": 84,
89
  "|": 1,
90
- "¥": 86,
91
- "«": 87,
92
- "®": 88,
93
- "·": 89,
94
- "Ï": 90,
95
- "è": 91,
96
- "é": 92,
97
- "÷": 93,
98
- "": 94,
99
- "": 95,
100
- "": 96,
101
- "": 97,
102
- "": 98,
103
- "": 99,
104
- "": 100,
105
- "": 101,
106
- "": 102,
107
- "": 103,
108
- "": 104,
109
- "": 105,
110
- "": 106,
111
- "": 107,
112
- "": 108,
113
- "": 109,
114
- "": 110,
115
- "": 111,
116
- "": 112,
117
- "": 113,
118
- "": 114,
119
- "": 115,
120
- "": 116,
121
- "": 117,
122
- "": 118,
123
- "": 119,
124
- "": 120,
125
- "": 121,
126
- "": 122,
127
- "": 123,
128
- "": 124,
129
- "": 125,
130
- "": 126,
131
- "": 127,
132
- "": 128,
133
- "": 129,
134
- "": 130,
135
- "": 131,
136
- "": 132,
137
- "": 133,
138
- "": 134,
139
- "": 135,
140
- "": 136,
141
- "": 137,
142
- "": 138,
143
- "": 139,
144
- "": 140,
145
- "": 141,
146
- "": 142,
147
- "ि": 143,
148
- "": 144,
149
- "": 145,
150
- "": 146,
151
- "": 147,
152
- "": 148,
153
- "": 149,
154
- "": 150,
155
- "": 151,
156
- "": 152,
157
- "": 153,
158
- "": 154,
159
- "": 155,
160
- "": 156,
161
- "": 157,
162
- "": 158,
163
- "": 159,
164
- "": 160,
165
- "": 161,
166
- "": 162,
167
- "": 163,
168
- "": 164,
169
- "": 165,
170
- "": 166,
171
- "": 167,
172
- "": 168,
173
- "": 169,
174
- "": 170,
175
- "": 171,
176
- "": 172,
177
- "": 173,
178
- "…": 174,
179
- " ": 175
180
  }
181
  }
 
3
  "\n": 0,
4
  "!": 2,
5
  "\"": 3,
6
+ "%": 4,
7
+ "'": 5,
8
+ "(": 6,
9
+ ")": 7,
10
+ ",": 8,
11
+ "-": 9,
12
+ ".": 10,
13
+ "/": 11,
14
+ "0": 12,
15
+ "1": 13,
16
+ "2": 14,
17
+ "3": 15,
18
+ "4": 16,
19
+ "5": 17,
20
+ "6": 18,
21
+ "7": 19,
22
+ "8": 20,
23
+ "9": 21,
24
+ ":": 22,
25
+ ";": 23,
26
+ "?": 24,
27
+ "A": 25,
28
+ "D": 26,
29
+ "M": 27,
30
+ "N": 28,
31
+ "R": 29,
32
+ "S": 30,
33
+ "[": 31,
34
+ "[PAD]": 146,
35
+ "[UNK]": 145,
36
+ "]": 32,
37
+ "_": 33,
38
+ "`": 34,
39
+ "a": 35,
40
+ "b": 36,
41
+ "c": 37,
42
+ "d": 38,
43
+ "e": 39,
44
+ "g": 40,
45
+ "h": 41,
46
+ "i": 42,
47
+ "j": 43,
48
+ "k": 44,
49
+ "l": 45,
50
+ "m": 46,
51
+ "n": 47,
52
+ "o": 48,
53
+ "p": 49,
54
+ "r": 50,
55
+ "s": 51,
56
+ "t": 52,
57
+ "v": 53,
58
+ "w": 54,
59
+ "x": 55,
60
+ "y": 56,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  "|": 1,
62
+ "¥": 58,
63
+ "«": 59,
64
+ "®": 60,
65
+ "·": 61,
66
+ "Ï": 62,
67
+ "÷": 63,
68
+ "": 64,
69
+ "": 65,
70
+ "": 66,
71
+ "": 67,
72
+ "": 68,
73
+ "": 69,
74
+ "": 70,
75
+ "": 71,
76
+ "": 72,
77
+ "": 73,
78
+ "": 74,
79
+ "": 75,
80
+ "": 76,
81
+ "": 77,
82
+ "": 78,
83
+ "": 79,
84
+ "": 80,
85
+ "": 81,
86
+ "": 82,
87
+ "": 83,
88
+ "": 84,
89
+ "": 85,
90
+ "": 86,
91
+ "": 87,
92
+ "": 88,
93
+ "": 89,
94
+ "": 90,
95
+ "": 91,
96
+ "": 92,
97
+ "": 93,
98
+ "": 94,
99
+ "": 95,
100
+ "": 96,
101
+ "": 97,
102
+ "": 98,
103
+ "": 99,
104
+ "": 100,
105
+ "": 101,
106
+ "": 102,
107
+ "": 103,
108
+ "": 104,
109
+ "": 105,
110
+ "": 106,
111
+ "": 107,
112
+ "": 108,
113
+ "": 109,
114
+ "": 110,
115
+ "": 111,
116
+ "": 112,
117
+ "ि": 113,
118
+ "": 114,
119
+ "": 115,
120
+ "": 116,
121
+ "": 117,
122
+ "": 118,
123
+ "": 119,
124
+ "": 120,
125
+ "": 121,
126
+ "": 122,
127
+ "": 123,
128
+ "": 124,
129
+ "": 125,
130
+ "": 126,
131
+ "": 127,
132
+ "": 128,
133
+ "": 129,
134
+ "": 130,
135
+ "": 131,
136
+ "": 132,
137
+ "": 133,
138
+ "": 134,
139
+ "": 135,
140
+ "": 136,
141
+ "": 137,
142
+ "": 138,
143
+ "": 139,
144
+ "": 140,
145
+ "": 141,
146
+ "": 142,
147
+ "": 143,
148
+ "": 144,
149
+ "": 145
 
 
150
  }
151
  }