abdulhade commited on
Commit
ab6e6dd
1 Parent(s): 069126e

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +263 -0
  2. special_tokens_map.json +240 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +2325 -0
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|af|>": 50221,
3
+ "<|am|>": 50228,
4
+ "<|as|>": 50244,
5
+ "<|az|>": 50198,
6
+ "<|ba|>": 50249,
7
+ "<|be|>": 50224,
8
+ "<|bg|>": 50186,
9
+ "<|bn|>": 50196,
10
+ "<|bo|>": 50241,
11
+ "<|br|>": 50203,
12
+ "<|bs|>": 50209,
13
+ "<|cy|>": 50191,
14
+ "<|endoftext|>": 50000,
15
+ "<|et|>": 50201,
16
+ "<|eu|>": 50204,
17
+ "<|fa|>": 50194,
18
+ "<|fo|>": 50232,
19
+ "<|gl|>": 50213,
20
+ "<|gu|>": 50227,
21
+ "<|haw|>": 50246,
22
+ "<|ha|>": 50248,
23
+ "<|hr|>": 50185,
24
+ "<|ht|>": 50233,
25
+ "<|hu|>": 50180,
26
+ "<|hy|>": 50206,
27
+ "<|is|>": 50205,
28
+ "<|jw|>": 50250,
29
+ "<|ka|>": 50223,
30
+ "<|kk|>": 50210,
31
+ "<|km|>": 50217,
32
+ "<|kn|>": 50200,
33
+ "<|la|>": 50188,
34
+ "<|lb|>": 50239,
35
+ "<|ln|>": 50247,
36
+ "<|lo|>": 50230,
37
+ "<|lt|>": 50187,
38
+ "<|lv|>": 50195,
39
+ "<|mg|>": 50243,
40
+ "<|mi|>": 50189,
41
+ "<|mk|>": 50202,
42
+ "<|ml|>": 50190,
43
+ "<|mn|>": 50208,
44
+ "<|mr|>": 50214,
45
+ "<|mt|>": 50237,
46
+ "<|my|>": 50240,
47
+ "<|ne|>": 50207,
48
+ "<|nn|>": 50236,
49
+ "<|nocaptions|>": 50256,
50
+ "<|notimestamps|>": 50257,
51
+ "<|no|>": 50182,
52
+ "<|oc|>": 50222,
53
+ "<|pa|>": 50215,
54
+ "<|ps|>": 50234,
55
+ "<|sa|>": 50238,
56
+ "<|sd|>": 50226,
57
+ "<|si|>": 50216,
58
+ "<|sk|>": 50192,
59
+ "<|sl|>": 50199,
60
+ "<|sn|>": 50218,
61
+ "<|so|>": 50220,
62
+ "<|sq|>": 50211,
63
+ "<|sr|>": 50197,
64
+ "<|startoflm|>": 50254,
65
+ "<|startofprev|>": 50255,
66
+ "<|startoftranscript|>": 50258,
67
+ "<|su|>": 50251,
68
+ "<|sw|>": 50212,
69
+ "<|ta|>": 50181,
70
+ "<|te|>": 50193,
71
+ "<|tg|>": 50225,
72
+ "<|th|>": 50183,
73
+ "<|tk|>": 50235,
74
+ "<|tl|>": 50242,
75
+ "<|transcribe|>": 50253,
76
+ "<|translate|>": 50252,
77
+ "<|tt|>": 50245,
78
+ "<|ur|>": 50184,
79
+ "<|uz|>": 50231,
80
+ "<|yi|>": 50229,
81
+ "<|yo|>": 50219,
82
+ "<|¡|>": 50001,
83
+ "<|¢|>": 50002,
84
+ "<|£|>": 50003,
85
+ "<|¤|>": 50004,
86
+ "<|¥|>": 50005,
87
+ "<|¦|>": 50006,
88
+ "<|§|>": 50007,
89
+ "<|¨|>": 50008,
90
+ "<|©|>": 50009,
91
+ "<|ª|>": 50010,
92
+ "<|«|>": 50011,
93
+ "<|¬|>": 50012,
94
+ "<|®|>": 50013,
95
+ "<|¯|>": 50014,
96
+ "<|°|>": 50015,
97
+ "<|±|>": 50016,
98
+ "<|²|>": 50017,
99
+ "<|³|>": 50018,
100
+ "<|´|>": 50019,
101
+ "<|µ|>": 50020,
102
+ "<|¶|>": 50021,
103
+ "<|·|>": 50022,
104
+ "<|¸|>": 50023,
105
+ "<|¹|>": 50024,
106
+ "<|º|>": 50025,
107
+ "<|»|>": 50026,
108
+ "<|¼|>": 50027,
109
+ "<|½|>": 50028,
110
+ "<|¾|>": 50029,
111
+ "<|¿|>": 50030,
112
+ "<|À|>": 50031,
113
+ "<|Á|>": 50032,
114
+ "<|Â|>": 50033,
115
+ "<|Ã|>": 50034,
116
+ "<|Ä|>": 50035,
117
+ "<|Å|>": 50036,
118
+ "<|Æ|>": 50037,
119
+ "<|Ç|>": 50038,
120
+ "<|È|>": 50039,
121
+ "<|É|>": 50040,
122
+ "<|Ê|>": 50041,
123
+ "<|Ë|>": 50042,
124
+ "<|Ì|>": 50043,
125
+ "<|Í|>": 50044,
126
+ "<|Î|>": 50045,
127
+ "<|Ï|>": 50046,
128
+ "<|Ð|>": 50047,
129
+ "<|Ñ|>": 50048,
130
+ "<|Ò|>": 50049,
131
+ "<|Ó|>": 50050,
132
+ "<|Ô|>": 50051,
133
+ "<|Õ|>": 50052,
134
+ "<|Ö|>": 50053,
135
+ "<|×|>": 50054,
136
+ "<|Ø|>": 50055,
137
+ "<|ا|>": 50165,
138
+ "<|اÙĨ|>": 50173,
139
+ "<|ت|>": 50172,
140
+ "<|د|>": 50175,
141
+ "<|ر|>": 50169,
142
+ "<|س|>": 50179,
143
+ "<|Ù|>": 50056,
144
+ "<|Ùħ|>": 50176,
145
+ "<|ÙĨ|>": 50168,
146
+ "<|ÙĪ|>": 50167,
147
+ "<|Ú|>": 50057,
148
+ "<|Ú©|>": 50170,
149
+ "<|Û|>": 50058,
150
+ "<|ÛĨ|>": 50178,
151
+ "<|ÛĮ|>": 50164,
152
+ "<|Ûİ|>": 50174,
153
+ "<|Ûķ|>": 50163,
154
+ "<|Ü|>": 50059,
155
+ "<|Ý|>": 50060,
156
+ "<|Þ|>": 50061,
157
+ "<|ß|>": 50062,
158
+ "<|à|>": 50063,
159
+ "<|á|>": 50064,
160
+ "<|â|>": 50065,
161
+ "<|ã|>": 50066,
162
+ "<|ä|>": 50067,
163
+ "<|å|>": 50068,
164
+ "<|æ|>": 50069,
165
+ "<|ç|>": 50070,
166
+ "<|è|>": 50071,
167
+ "<|é|>": 50072,
168
+ "<|ê|>": 50073,
169
+ "<|ë|>": 50074,
170
+ "<|ì|>": 50075,
171
+ "<|í|>": 50076,
172
+ "<|î|>": 50077,
173
+ "<|ï|>": 50078,
174
+ "<|ð|>": 50079,
175
+ "<|ñ|>": 50080,
176
+ "<|ò|>": 50081,
177
+ "<|ó|>": 50082,
178
+ "<|ô|>": 50083,
179
+ "<|õ|>": 50084,
180
+ "<|ö|>": 50085,
181
+ "<|÷|>": 50086,
182
+ "<|ø|>": 50087,
183
+ "<|ù|>": 50088,
184
+ "<|ú|>": 50089,
185
+ "<|û|>": 50090,
186
+ "<|ü|>": 50091,
187
+ "<|ý|>": 50092,
188
+ "<|þ|>": 50093,
189
+ "<|ÿ|>": 50094,
190
+ "<|Ā|>": 50095,
191
+ "<|ā|>": 50096,
192
+ "<|Ă|>": 50097,
193
+ "<|ă|>": 50098,
194
+ "<|Ą|>": 50099,
195
+ "<|ą|>": 50100,
196
+ "<|Ć|>": 50101,
197
+ "<|ć|>": 50102,
198
+ "<|Ĉ|>": 50103,
199
+ "<|ĉ|>": 50104,
200
+ "<|Ċ|>": 50105,
201
+ "<|ċ|>": 50106,
202
+ "<|Č|>": 50107,
203
+ "<|č|>": 50108,
204
+ "<|Ď|>": 50109,
205
+ "<|ď|>": 50110,
206
+ "<|Đ|>": 50111,
207
+ "<|đ|>": 50112,
208
+ "<|Ē|>": 50113,
209
+ "<|ē|>": 50114,
210
+ "<|Ĕ|>": 50115,
211
+ "<|ĕ|>": 50116,
212
+ "<|Ė|>": 50117,
213
+ "<|ė|>": 50118,
214
+ "<|Ę|>": 50119,
215
+ "<|ę|>": 50120,
216
+ "<|Ě|>": 50121,
217
+ "<|ě|>": 50122,
218
+ "<|Ĝ|>": 50123,
219
+ "<|ĝ|>": 50124,
220
+ "<|Ğ|>": 50125,
221
+ "<|ğ|>": 50126,
222
+ "<|Ġ|>": 50127,
223
+ "<|ĠØ|>": 50166,
224
+ "<|Ġب|>": 50177,
225
+ "<|ĠÙ|>": 50171,
226
+ "<|ġ|>": 50128,
227
+ "<|Ģ|>": 50129,
228
+ "<|ģ|>": 50130,
229
+ "<|Ĥ|>": 50131,
230
+ "<|ĥ|>": 50132,
231
+ "<|Ħ|>": 50133,
232
+ "<|ħ|>": 50134,
233
+ "<|Ĩ|>": 50135,
234
+ "<|ĩ|>": 50136,
235
+ "<|Ī|>": 50137,
236
+ "<|ī|>": 50138,
237
+ "<|Ĭ|>": 50139,
238
+ "<|ĭ|>": 50140,
239
+ "<|Į|>": 50141,
240
+ "<|į|>": 50142,
241
+ "<|İ|>": 50143,
242
+ "<|ı|>": 50144,
243
+ "<|IJ|>": 50145,
244
+ "<|ij|>": 50146,
245
+ "<|Ĵ|>": 50147,
246
+ "<|ĵ|>": 50148,
247
+ "<|Ķ|>": 50149,
248
+ "<|ķ|>": 50150,
249
+ "<|ĸ|>": 50151,
250
+ "<|Ĺ|>": 50259,
251
+ "<|��|>": 50260,
252
+ "<|Ļ|>": 50154,
253
+ "<|ļ|>": 50155,
254
+ "<|Ľ|>": 50156,
255
+ "<|ľ|>": 50157,
256
+ "<|Ŀ|>": 50158,
257
+ "<|ŀ|>": 50159,
258
+ "<|Ł|>": 50160,
259
+ "<|ł|>": 50161,
260
+ "<|Ń|>": 50162,
261
+ "[new_token1]": 50152,
262
+ "[new_token2]": 50153
263
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|¡|>",
6
+ "<|¢|>",
7
+ "<|£|>",
8
+ "<|¤|>",
9
+ "<|¥|>",
10
+ "<|¦|>",
11
+ "<|§|>",
12
+ "<|¨|>",
13
+ "<|©|>",
14
+ "<|ª|>",
15
+ "<|«|>",
16
+ "<|¬|>",
17
+ "<|®|>",
18
+ "<|¯|>",
19
+ "<|°|>",
20
+ "<|±|>",
21
+ "<|²|>",
22
+ "<|³|>",
23
+ "<|´|>",
24
+ "<|µ|>",
25
+ "<|¶|>",
26
+ "<|·|>",
27
+ "<|¸|>",
28
+ "<|¹|>",
29
+ "<|º|>",
30
+ "<|»|>",
31
+ "<|¼|>",
32
+ "<|½|>",
33
+ "<|¾|>",
34
+ "<|¿|>",
35
+ "<|À|>",
36
+ "<|Á|>",
37
+ "<|Â|>",
38
+ "<|Ã|>",
39
+ "<|Ä|>",
40
+ "<|Å|>",
41
+ "<|Æ|>",
42
+ "<|Ç|>",
43
+ "<|È|>",
44
+ "<|É|>",
45
+ "<|Ê|>",
46
+ "<|Ë|>",
47
+ "<|Ì|>",
48
+ "<|Í|>",
49
+ "<|Î|>",
50
+ "<|Ï|>",
51
+ "<|Ð|>",
52
+ "<|Ñ|>",
53
+ "<|Ò|>",
54
+ "<|Ó|>",
55
+ "<|Ô|>",
56
+ "<|Õ|>",
57
+ "<|Ö|>",
58
+ "<|×|>",
59
+ "<|Ø|>",
60
+ "<|Ù|>",
61
+ "<|Ú|>",
62
+ "<|Û|>",
63
+ "<|Ü|>",
64
+ "<|Ý|>",
65
+ "<|Þ|>",
66
+ "<|ß|>",
67
+ "<|à|>",
68
+ "<|á|>",
69
+ "<|â|>",
70
+ "<|ã|>",
71
+ "<|ä|>",
72
+ "<|å|>",
73
+ "<|æ|>",
74
+ "<|ç|>",
75
+ "<|è|>",
76
+ "<|é|>",
77
+ "<|ê|>",
78
+ "<|ë|>",
79
+ "<|ì|>",
80
+ "<|í|>",
81
+ "<|î|>",
82
+ "<|ï|>",
83
+ "<|ð|>",
84
+ "<|ñ|>",
85
+ "<|ò|>",
86
+ "<|ó|>",
87
+ "<|ô|>",
88
+ "<|õ|>",
89
+ "<|ö|>",
90
+ "<|÷|>",
91
+ "<|ø|>",
92
+ "<|ù|>",
93
+ "<|ú|>",
94
+ "<|û|>",
95
+ "<|ü|>",
96
+ "<|ý|>",
97
+ "<|þ|>",
98
+ "<|ÿ|>",
99
+ "<|Ā|>",
100
+ "<|ā|>",
101
+ "<|Ă|>",
102
+ "<|ă|>",
103
+ "<|Ą|>",
104
+ "<|ą|>",
105
+ "<|Ć|>",
106
+ "<|ć|>",
107
+ "<|Ĉ|>",
108
+ "<|ĉ|>",
109
+ "<|Ċ|>",
110
+ "<|ċ|>",
111
+ "<|Č|>",
112
+ "<|č|>",
113
+ "<|Ď|>",
114
+ "<|ď|>",
115
+ "<|Đ|>",
116
+ "<|đ|>",
117
+ "<|Ē|>",
118
+ "<|ē|>",
119
+ "<|Ĕ|>",
120
+ "<|ĕ|>",
121
+ "<|Ė|>",
122
+ "<|ė|>",
123
+ "<|Ę|>",
124
+ "<|ę|>",
125
+ "<|Ě|>",
126
+ "<|ě|>",
127
+ "<|Ĝ|>",
128
+ "<|ĝ|>",
129
+ "<|Ğ|>",
130
+ "<|ğ|>",
131
+ "<|Ġ|>",
132
+ "<|ġ|>",
133
+ "<|Ģ|>",
134
+ "<|ģ|>",
135
+ "<|Ĥ|>",
136
+ "<|ĥ|>",
137
+ "<|Ħ|>",
138
+ "<|ħ|>",
139
+ "<|Ĩ|>",
140
+ "<|ĩ|>",
141
+ "<|Ī|>",
142
+ "<|ī|>",
143
+ "<|Ĭ|>",
144
+ "<|ĭ|>",
145
+ "<|Į|>",
146
+ "<|į|>",
147
+ "<|İ|>",
148
+ "<|ı|>",
149
+ "<|IJ|>",
150
+ "<|ij|>",
151
+ "<|Ĵ|>",
152
+ "<|ĵ|>",
153
+ "<|Ķ|>",
154
+ "<|ķ|>",
155
+ "<|ĸ|>",
156
+ "<|Ĺ|>",
157
+ "<|ĺ|>",
158
+ "<|Ļ|>",
159
+ "<|ļ|>",
160
+ "<|Ľ|>",
161
+ "<|ľ|>",
162
+ "<|Ŀ|>",
163
+ "<|ŀ|>",
164
+ "<|Ł|>",
165
+ "<|ł|>",
166
+ "<|Ń|>",
167
+ "<|Ûķ|>",
168
+ "<|ÛĮ|>",
169
+ "<|ا|>",
170
+ "<|ĠØ|>",
171
+ "<|ÙĪ|>",
172
+ "<|ÙĨ|>",
173
+ "<|ر|>",
174
+ "<|Ú©|>",
175
+ "<|ĠÙ|>",
176
+ "<|ت|>",
177
+ "<|اÙĨ|>",
178
+ "<|Ûİ|>",
179
+ "<|د|>",
180
+ "<|Ùħ|>",
181
+ "<|Ġب|>",
182
+ "<|ÛĨ|>",
183
+ "<|س|>",
184
+ "<|translate|>",
185
+ "<|transcribe|>",
186
+ "<|startoflm|>",
187
+ "<|startofprev|>",
188
+ "<|nocaptions|>",
189
+ "<|notimestamps|>"
190
+ ],
191
+ "bos_token": {
192
+ "content": "<|endoftext|>",
193
+ "lstrip": false,
194
+ "normalized": true,
195
+ "rstrip": false,
196
+ "single_word": false
197
+ },
198
+ "cls_token": {
199
+ "content": "[CLS]",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false
204
+ },
205
+ "eos_token": {
206
+ "content": "<|endoftext|>",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false
211
+ },
212
+ "mask_token": {
213
+ "content": "[MASK]",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false
218
+ },
219
+ "pad_token": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false
225
+ },
226
+ "sep_token": {
227
+ "content": "[SEP]",
228
+ "lstrip": false,
229
+ "normalized": false,
230
+ "rstrip": false,
231
+ "single_word": false
232
+ },
233
+ "unk_token": {
234
+ "content": "<|endoftext|>",
235
+ "lstrip": false,
236
+ "normalized": true,
237
+ "rstrip": false,
238
+ "single_word": false
239
+ }
240
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "2": {
6
+ "content": "[CLS]",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "3": {
14
+ "content": "[SEP]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "4": {
22
+ "content": "[MASK]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50001": {
38
+ "content": "<|¡|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50002": {
46
+ "content": "<|¢|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50003": {
54
+ "content": "<|£|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50004": {
62
+ "content": "<|¤|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50005": {
70
+ "content": "<|¥|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50006": {
78
+ "content": "<|¦|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50007": {
86
+ "content": "<|§|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50008": {
94
+ "content": "<|¨|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "50009": {
102
+ "content": "<|©|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "50010": {
110
+ "content": "<|ª|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "50011": {
118
+ "content": "<|«|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "50012": {
126
+ "content": "<|¬|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "50013": {
134
+ "content": "<|®|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "50014": {
142
+ "content": "<|¯|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "50015": {
150
+ "content": "<|°|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "50016": {
158
+ "content": "<|±|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "50017": {
166
+ "content": "<|²|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "50018": {
174
+ "content": "<|³|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "50019": {
182
+ "content": "<|´|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "50020": {
190
+ "content": "<|µ|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "50021": {
198
+ "content": "<|¶|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "50022": {
206
+ "content": "<|·|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "50023": {
214
+ "content": "<|¸|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "50024": {
222
+ "content": "<|¹|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "50025": {
230
+ "content": "<|º|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "50026": {
238
+ "content": "<|»|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "50027": {
246
+ "content": "<|¼|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "50028": {
254
+ "content": "<|½|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "50029": {
262
+ "content": "<|¾|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "50030": {
270
+ "content": "<|¿|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "50031": {
278
+ "content": "<|À|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "50032": {
286
+ "content": "<|Á|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "50033": {
294
+ "content": "<|Â|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "50034": {
302
+ "content": "<|Ã|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "50035": {
310
+ "content": "<|Ä|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "50036": {
318
+ "content": "<|Å|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "50037": {
326
+ "content": "<|Æ|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "50038": {
334
+ "content": "<|Ç|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "50039": {
342
+ "content": "<|È|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "50040": {
350
+ "content": "<|É|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "50041": {
358
+ "content": "<|Ê|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "50042": {
366
+ "content": "<|Ë|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "50043": {
374
+ "content": "<|Ì|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "50044": {
382
+ "content": "<|Í|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "50045": {
390
+ "content": "<|Î|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "50046": {
398
+ "content": "<|Ï|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "50047": {
406
+ "content": "<|Ð|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "50048": {
414
+ "content": "<|Ñ|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "50049": {
422
+ "content": "<|Ò|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "50050": {
430
+ "content": "<|Ó|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "50051": {
438
+ "content": "<|Ô|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "50052": {
446
+ "content": "<|Õ|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "50053": {
454
+ "content": "<|Ö|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "50054": {
462
+ "content": "<|×|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "50055": {
470
+ "content": "<|Ø|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "50056": {
478
+ "content": "<|Ù|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "50057": {
486
+ "content": "<|Ú|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "50058": {
494
+ "content": "<|Û|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "50059": {
502
+ "content": "<|Ü|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "50060": {
510
+ "content": "<|Ý|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "50061": {
518
+ "content": "<|Þ|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "50062": {
526
+ "content": "<|ß|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "50063": {
534
+ "content": "<|à|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "50064": {
542
+ "content": "<|á|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "50065": {
550
+ "content": "<|â|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "50066": {
558
+ "content": "<|ã|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "50067": {
566
+ "content": "<|ä|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "50068": {
574
+ "content": "<|å|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "50069": {
582
+ "content": "<|æ|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "50070": {
590
+ "content": "<|ç|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "50071": {
598
+ "content": "<|è|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "50072": {
606
+ "content": "<|é|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "50073": {
614
+ "content": "<|ê|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "50074": {
622
+ "content": "<|ë|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "50075": {
630
+ "content": "<|ì|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "50076": {
638
+ "content": "<|í|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "50077": {
646
+ "content": "<|î|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "50078": {
654
+ "content": "<|ï|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "50079": {
662
+ "content": "<|ð|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "50080": {
670
+ "content": "<|ñ|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "50081": {
678
+ "content": "<|ò|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "50082": {
686
+ "content": "<|ó|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "50083": {
694
+ "content": "<|ô|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "50084": {
702
+ "content": "<|õ|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "50085": {
710
+ "content": "<|ö|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "50086": {
718
+ "content": "<|÷|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "50087": {
726
+ "content": "<|ø|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "50088": {
734
+ "content": "<|ù|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "50089": {
742
+ "content": "<|ú|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "50090": {
750
+ "content": "<|û|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "50091": {
758
+ "content": "<|ü|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "50092": {
766
+ "content": "<|ý|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "50093": {
774
+ "content": "<|þ|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "50094": {
782
+ "content": "<|ÿ|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "50095": {
790
+ "content": "<|Ā|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "50096": {
798
+ "content": "<|ā|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "50097": {
806
+ "content": "<|Ă|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "50098": {
814
+ "content": "<|ă|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "50099": {
822
+ "content": "<|Ą|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "50100": {
830
+ "content": "<|ą|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "50101": {
838
+ "content": "<|Ć|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "50102": {
846
+ "content": "<|ć|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "50103": {
854
+ "content": "<|Ĉ|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "50104": {
862
+ "content": "<|ĉ|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "50105": {
870
+ "content": "<|Ċ|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "50106": {
878
+ "content": "<|ċ|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "50107": {
886
+ "content": "<|Č|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "50108": {
894
+ "content": "<|č|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "50109": {
902
+ "content": "<|Ď|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "50110": {
910
+ "content": "<|ď|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "50111": {
918
+ "content": "<|Đ|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "50112": {
926
+ "content": "<|đ|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "50113": {
934
+ "content": "<|Ē|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "50114": {
942
+ "content": "<|ē|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "50115": {
950
+ "content": "<|Ĕ|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "50116": {
958
+ "content": "<|ĕ|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "50117": {
966
+ "content": "<|Ė|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "50118": {
974
+ "content": "<|ė|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "50119": {
982
+ "content": "<|Ę|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "50120": {
990
+ "content": "<|ę|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "50121": {
998
+ "content": "<|Ě|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "50122": {
1006
+ "content": "<|ě|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "50123": {
1014
+ "content": "<|Ĝ|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "50124": {
1022
+ "content": "<|ĝ|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "50125": {
1030
+ "content": "<|Ğ|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "50126": {
1038
+ "content": "<|ğ|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "50127": {
1046
+ "content": "<|Ġ|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "50128": {
1054
+ "content": "<|ġ|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "50129": {
1062
+ "content": "<|Ģ|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "50130": {
1070
+ "content": "<|ģ|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "50131": {
1078
+ "content": "<|Ĥ|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "50132": {
1086
+ "content": "<|ĥ|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "50133": {
1094
+ "content": "<|Ħ|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "50134": {
1102
+ "content": "<|ħ|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "50135": {
1110
+ "content": "<|Ĩ|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "50136": {
1118
+ "content": "<|ĩ|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "50137": {
1126
+ "content": "<|Ī|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "50138": {
1134
+ "content": "<|ī|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "50139": {
1142
+ "content": "<|Ĭ|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "50140": {
1150
+ "content": "<|ĭ|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "50141": {
1158
+ "content": "<|Į|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "50142": {
1166
+ "content": "<|į|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "50143": {
1174
+ "content": "<|İ|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "50144": {
1182
+ "content": "<|ı|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "50145": {
1190
+ "content": "<|IJ|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "50146": {
1198
+ "content": "<|ij|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "50147": {
1206
+ "content": "<|Ĵ|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "50148": {
1214
+ "content": "<|ĵ|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "50149": {
1222
+ "content": "<|Ķ|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "50150": {
1230
+ "content": "<|ķ|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "50151": {
1238
+ "content": "<|ĸ|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "50152": {
1246
+ "content": "[new_token1]",
1247
+ "lstrip": false,
1248
+ "normalized": true,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "50153": {
1254
+ "content": "[new_token2]",
1255
+ "lstrip": false,
1256
+ "normalized": true,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "50154": {
1262
+ "content": "<|Ļ|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "50155": {
1270
+ "content": "<|ļ|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "50156": {
1278
+ "content": "<|Ľ|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "50157": {
1286
+ "content": "<|ľ|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "50158": {
1294
+ "content": "<|Ŀ|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "50159": {
1302
+ "content": "<|ŀ|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "50160": {
1310
+ "content": "<|Ł|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "50161": {
1318
+ "content": "<|ł|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "50162": {
1326
+ "content": "<|Ń|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "50163": {
1334
+ "content": "<|Ûķ|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "50164": {
1342
+ "content": "<|ÛĮ|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "50165": {
1350
+ "content": "<|ا|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "50166": {
1358
+ "content": "<|ĠØ|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "50167": {
1366
+ "content": "<|ÙĪ|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "50168": {
1374
+ "content": "<|ÙĨ|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "50169": {
1382
+ "content": "<|ر|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "50170": {
1390
+ "content": "<|Ú©|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "50171": {
1398
+ "content": "<|ĠÙ|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "50172": {
1406
+ "content": "<|ت|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "50173": {
1414
+ "content": "<|اÙĨ|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "50174": {
1422
+ "content": "<|Ûİ|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "50175": {
1430
+ "content": "<|د|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "50176": {
1438
+ "content": "<|Ùħ|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "50177": {
1446
+ "content": "<|Ġب|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "50178": {
1454
+ "content": "<|ÛĨ|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "50179": {
1462
+ "content": "<|س|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "50180": {
1470
+ "content": "<|hu|>",
1471
+ "lstrip": false,
1472
+ "normalized": true,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "50181": {
1478
+ "content": "<|ta|>",
1479
+ "lstrip": false,
1480
+ "normalized": true,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "50182": {
1486
+ "content": "<|no|>",
1487
+ "lstrip": false,
1488
+ "normalized": true,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "50183": {
1494
+ "content": "<|th|>",
1495
+ "lstrip": false,
1496
+ "normalized": true,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "50184": {
1502
+ "content": "<|ur|>",
1503
+ "lstrip": false,
1504
+ "normalized": true,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "50185": {
1510
+ "content": "<|hr|>",
1511
+ "lstrip": false,
1512
+ "normalized": true,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "50186": {
1518
+ "content": "<|bg|>",
1519
+ "lstrip": false,
1520
+ "normalized": true,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "50187": {
1526
+ "content": "<|lt|>",
1527
+ "lstrip": false,
1528
+ "normalized": true,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "50188": {
1534
+ "content": "<|la|>",
1535
+ "lstrip": false,
1536
+ "normalized": true,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "50189": {
1542
+ "content": "<|mi|>",
1543
+ "lstrip": false,
1544
+ "normalized": true,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "50190": {
1550
+ "content": "<|ml|>",
1551
+ "lstrip": false,
1552
+ "normalized": true,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "50191": {
1558
+ "content": "<|cy|>",
1559
+ "lstrip": false,
1560
+ "normalized": true,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "50192": {
1566
+ "content": "<|sk|>",
1567
+ "lstrip": false,
1568
+ "normalized": true,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "50193": {
1574
+ "content": "<|te|>",
1575
+ "lstrip": false,
1576
+ "normalized": true,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "50194": {
1582
+ "content": "<|fa|>",
1583
+ "lstrip": false,
1584
+ "normalized": true,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "50195": {
1590
+ "content": "<|lv|>",
1591
+ "lstrip": false,
1592
+ "normalized": true,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "50196": {
1598
+ "content": "<|bn|>",
1599
+ "lstrip": false,
1600
+ "normalized": true,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "50197": {
1606
+ "content": "<|sr|>",
1607
+ "lstrip": false,
1608
+ "normalized": true,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "50198": {
1614
+ "content": "<|az|>",
1615
+ "lstrip": false,
1616
+ "normalized": true,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "50199": {
1622
+ "content": "<|sl|>",
1623
+ "lstrip": false,
1624
+ "normalized": true,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "50200": {
1630
+ "content": "<|kn|>",
1631
+ "lstrip": false,
1632
+ "normalized": true,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "50201": {
1638
+ "content": "<|et|>",
1639
+ "lstrip": false,
1640
+ "normalized": true,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "50202": {
1646
+ "content": "<|mk|>",
1647
+ "lstrip": false,
1648
+ "normalized": true,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "50203": {
1654
+ "content": "<|br|>",
1655
+ "lstrip": false,
1656
+ "normalized": true,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "50204": {
1662
+ "content": "<|eu|>",
1663
+ "lstrip": false,
1664
+ "normalized": true,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "50205": {
1670
+ "content": "<|is|>",
1671
+ "lstrip": false,
1672
+ "normalized": true,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "50206": {
1678
+ "content": "<|hy|>",
1679
+ "lstrip": false,
1680
+ "normalized": true,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "50207": {
1686
+ "content": "<|ne|>",
1687
+ "lstrip": false,
1688
+ "normalized": true,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "50208": {
1694
+ "content": "<|mn|>",
1695
+ "lstrip": false,
1696
+ "normalized": true,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "50209": {
1702
+ "content": "<|bs|>",
1703
+ "lstrip": false,
1704
+ "normalized": true,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "50210": {
1710
+ "content": "<|kk|>",
1711
+ "lstrip": false,
1712
+ "normalized": true,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "50211": {
1718
+ "content": "<|sq|>",
1719
+ "lstrip": false,
1720
+ "normalized": true,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "50212": {
1726
+ "content": "<|sw|>",
1727
+ "lstrip": false,
1728
+ "normalized": true,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "50213": {
1734
+ "content": "<|gl|>",
1735
+ "lstrip": false,
1736
+ "normalized": true,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "50214": {
1742
+ "content": "<|mr|>",
1743
+ "lstrip": false,
1744
+ "normalized": true,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "50215": {
1750
+ "content": "<|pa|>",
1751
+ "lstrip": false,
1752
+ "normalized": true,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "50216": {
1758
+ "content": "<|si|>",
1759
+ "lstrip": false,
1760
+ "normalized": true,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "50217": {
1766
+ "content": "<|km|>",
1767
+ "lstrip": false,
1768
+ "normalized": true,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "50218": {
1774
+ "content": "<|sn|>",
1775
+ "lstrip": false,
1776
+ "normalized": true,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "50219": {
1782
+ "content": "<|yo|>",
1783
+ "lstrip": false,
1784
+ "normalized": true,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "50220": {
1790
+ "content": "<|so|>",
1791
+ "lstrip": false,
1792
+ "normalized": true,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "50221": {
1798
+ "content": "<|af|>",
1799
+ "lstrip": false,
1800
+ "normalized": true,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "50222": {
1806
+ "content": "<|oc|>",
1807
+ "lstrip": false,
1808
+ "normalized": true,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "50223": {
1814
+ "content": "<|ka|>",
1815
+ "lstrip": false,
1816
+ "normalized": true,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "50224": {
1822
+ "content": "<|be|>",
1823
+ "lstrip": false,
1824
+ "normalized": true,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "50225": {
1830
+ "content": "<|tg|>",
1831
+ "lstrip": false,
1832
+ "normalized": true,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "50226": {
1838
+ "content": "<|sd|>",
1839
+ "lstrip": false,
1840
+ "normalized": true,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "50227": {
1846
+ "content": "<|gu|>",
1847
+ "lstrip": false,
1848
+ "normalized": true,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "50228": {
1854
+ "content": "<|am|>",
1855
+ "lstrip": false,
1856
+ "normalized": true,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "50229": {
1862
+ "content": "<|yi|>",
1863
+ "lstrip": false,
1864
+ "normalized": true,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "50230": {
1870
+ "content": "<|lo|>",
1871
+ "lstrip": false,
1872
+ "normalized": true,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "50231": {
1878
+ "content": "<|uz|>",
1879
+ "lstrip": false,
1880
+ "normalized": true,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "50232": {
1886
+ "content": "<|fo|>",
1887
+ "lstrip": false,
1888
+ "normalized": true,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "50233": {
1894
+ "content": "<|ht|>",
1895
+ "lstrip": false,
1896
+ "normalized": true,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "50234": {
1902
+ "content": "<|ps|>",
1903
+ "lstrip": false,
1904
+ "normalized": true,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "50235": {
1910
+ "content": "<|tk|>",
1911
+ "lstrip": false,
1912
+ "normalized": true,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "50236": {
1918
+ "content": "<|nn|>",
1919
+ "lstrip": false,
1920
+ "normalized": true,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "50237": {
1926
+ "content": "<|mt|>",
1927
+ "lstrip": false,
1928
+ "normalized": true,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "50238": {
1934
+ "content": "<|sa|>",
1935
+ "lstrip": false,
1936
+ "normalized": true,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "50239": {
1942
+ "content": "<|lb|>",
1943
+ "lstrip": false,
1944
+ "normalized": true,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "50240": {
1950
+ "content": "<|my|>",
1951
+ "lstrip": false,
1952
+ "normalized": true,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "50241": {
1958
+ "content": "<|bo|>",
1959
+ "lstrip": false,
1960
+ "normalized": true,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "50242": {
1966
+ "content": "<|tl|>",
1967
+ "lstrip": false,
1968
+ "normalized": true,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "50243": {
1974
+ "content": "<|mg|>",
1975
+ "lstrip": false,
1976
+ "normalized": true,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "50244": {
1982
+ "content": "<|as|>",
1983
+ "lstrip": false,
1984
+ "normalized": true,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "50245": {
1990
+ "content": "<|tt|>",
1991
+ "lstrip": false,
1992
+ "normalized": true,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ },
1997
+ "50246": {
1998
+ "content": "<|haw|>",
1999
+ "lstrip": false,
2000
+ "normalized": true,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": false
2004
+ },
2005
+ "50247": {
2006
+ "content": "<|ln|>",
2007
+ "lstrip": false,
2008
+ "normalized": true,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": false
2012
+ },
2013
+ "50248": {
2014
+ "content": "<|ha|>",
2015
+ "lstrip": false,
2016
+ "normalized": true,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": false
2020
+ },
2021
+ "50249": {
2022
+ "content": "<|ba|>",
2023
+ "lstrip": false,
2024
+ "normalized": true,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": false
2028
+ },
2029
+ "50250": {
2030
+ "content": "<|jw|>",
2031
+ "lstrip": false,
2032
+ "normalized": true,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": false
2036
+ },
2037
+ "50251": {
2038
+ "content": "<|su|>",
2039
+ "lstrip": false,
2040
+ "normalized": true,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": false
2044
+ },
2045
+ "50252": {
2046
+ "content": "<|translate|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "50253": {
2054
+ "content": "<|transcribe|>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "50254": {
2062
+ "content": "<|startoflm|>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "50255": {
2070
+ "content": "<|startofprev|>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ },
2077
+ "50256": {
2078
+ "content": "<|nocaptions|>",
2079
+ "lstrip": false,
2080
+ "normalized": false,
2081
+ "rstrip": false,
2082
+ "single_word": false,
2083
+ "special": true
2084
+ },
2085
+ "50257": {
2086
+ "content": "<|notimestamps|>",
2087
+ "lstrip": false,
2088
+ "normalized": false,
2089
+ "rstrip": false,
2090
+ "single_word": false,
2091
+ "special": true
2092
+ },
2093
+ "50258": {
2094
+ "content": "<|startoftranscript|>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": true
2100
+ },
2101
+ "50259": {
2102
+ "content": "<|Ĺ|>",
2103
+ "lstrip": false,
2104
+ "normalized": false,
2105
+ "rstrip": false,
2106
+ "single_word": false,
2107
+ "special": true
2108
+ },
2109
+ "50260": {
2110
+ "content": "<|ĺ|>",
2111
+ "lstrip": false,
2112
+ "normalized": false,
2113
+ "rstrip": false,
2114
+ "single_word": false,
2115
+ "special": true
2116
+ }
2117
+ },
2118
+ "additional_special_tokens": [
2119
+ "<|endoftext|>",
2120
+ "<|startoftranscript|>",
2121
+ "<|¡|>",
2122
+ "<|¢|>",
2123
+ "<|£|>",
2124
+ "<|¤|>",
2125
+ "<|¥|>",
2126
+ "<|¦|>",
2127
+ "<|§|>",
2128
+ "<|¨|>",
2129
+ "<|©|>",
2130
+ "<|ª|>",
2131
+ "<|«|>",
2132
+ "<|¬|>",
2133
+ "<|®|>",
2134
+ "<|¯|>",
2135
+ "<|°|>",
2136
+ "<|±|>",
2137
+ "<|²|>",
2138
+ "<|³|>",
2139
+ "<|´|>",
2140
+ "<|µ|>",
2141
+ "<|¶|>",
2142
+ "<|·|>",
2143
+ "<|¸|>",
2144
+ "<|¹|>",
2145
+ "<|º|>",
2146
+ "<|»|>",
2147
+ "<|¼|>",
2148
+ "<|½|>",
2149
+ "<|¾|>",
2150
+ "<|¿|>",
2151
+ "<|À|>",
2152
+ "<|Á|>",
2153
+ "<|Â|>",
2154
+ "<|Ã|>",
2155
+ "<|Ä|>",
2156
+ "<|Å|>",
2157
+ "<|Æ|>",
2158
+ "<|Ç|>",
2159
+ "<|È|>",
2160
+ "<|É|>",
2161
+ "<|Ê|>",
2162
+ "<|Ë|>",
2163
+ "<|Ì|>",
2164
+ "<|Í|>",
2165
+ "<|Î|>",
2166
+ "<|Ï|>",
2167
+ "<|Ð|>",
2168
+ "<|Ñ|>",
2169
+ "<|Ò|>",
2170
+ "<|Ó|>",
2171
+ "<|Ô|>",
2172
+ "<|Õ|>",
2173
+ "<|Ö|>",
2174
+ "<|×|>",
2175
+ "<|Ø|>",
2176
+ "<|Ù|>",
2177
+ "<|Ú|>",
2178
+ "<|Û|>",
2179
+ "<|Ü|>",
2180
+ "<|Ý|>",
2181
+ "<|Þ|>",
2182
+ "<|ß|>",
2183
+ "<|à|>",
2184
+ "<|á|>",
2185
+ "<|â|>",
2186
+ "<|ã|>",
2187
+ "<|ä|>",
2188
+ "<|å|>",
2189
+ "<|æ|>",
2190
+ "<|ç|>",
2191
+ "<|è|>",
2192
+ "<|é|>",
2193
+ "<|ê|>",
2194
+ "<|ë|>",
2195
+ "<|ì|>",
2196
+ "<|í|>",
2197
+ "<|î|>",
2198
+ "<|ï|>",
2199
+ "<|ð|>",
2200
+ "<|ñ|>",
2201
+ "<|ò|>",
2202
+ "<|ó|>",
2203
+ "<|ô|>",
2204
+ "<|õ|>",
2205
+ "<|ö|>",
2206
+ "<|÷|>",
2207
+ "<|ø|>",
2208
+ "<|ù|>",
2209
+ "<|ú|>",
2210
+ "<|û|>",
2211
+ "<|ü|>",
2212
+ "<|ý|>",
2213
+ "<|þ|>",
2214
+ "<|ÿ|>",
2215
+ "<|Ā|>",
2216
+ "<|ā|>",
2217
+ "<|Ă|>",
2218
+ "<|ă|>",
2219
+ "<|Ą|>",
2220
+ "<|ą|>",
2221
+ "<|Ć|>",
2222
+ "<|ć|>",
2223
+ "<|Ĉ|>",
2224
+ "<|ĉ|>",
2225
+ "<|Ċ|>",
2226
+ "<|ċ|>",
2227
+ "<|Č|>",
2228
+ "<|č|>",
2229
+ "<|Ď|>",
2230
+ "<|ď|>",
2231
+ "<|Đ|>",
2232
+ "<|đ|>",
2233
+ "<|Ē|>",
2234
+ "<|ē|>",
2235
+ "<|Ĕ|>",
2236
+ "<|ĕ|>",
2237
+ "<|Ė|>",
2238
+ "<|ė|>",
2239
+ "<|Ę|>",
2240
+ "<|ę|>",
2241
+ "<|Ě|>",
2242
+ "<|ě|>",
2243
+ "<|Ĝ|>",
2244
+ "<|ĝ|>",
2245
+ "<|Ğ|>",
2246
+ "<|ğ|>",
2247
+ "<|Ġ|>",
2248
+ "<|ġ|>",
2249
+ "<|Ģ|>",
2250
+ "<|ģ|>",
2251
+ "<|Ĥ|>",
2252
+ "<|ĥ|>",
2253
+ "<|Ħ|>",
2254
+ "<|ħ|>",
2255
+ "<|Ĩ|>",
2256
+ "<|ĩ|>",
2257
+ "<|Ī|>",
2258
+ "<|ī|>",
2259
+ "<|Ĭ|>",
2260
+ "<|ĭ|>",
2261
+ "<|Į|>",
2262
+ "<|į|>",
2263
+ "<|İ|>",
2264
+ "<|ı|>",
2265
+ "<|IJ|>",
2266
+ "<|ij|>",
2267
+ "<|Ĵ|>",
2268
+ "<|ĵ|>",
2269
+ "<|Ķ|>",
2270
+ "<|ķ|>",
2271
+ "<|ĸ|>",
2272
+ "<|Ĺ|>",
2273
+ "<|ĺ|>",
2274
+ "<|Ļ|>",
2275
+ "<|ļ|>",
2276
+ "<|Ľ|>",
2277
+ "<|ľ|>",
2278
+ "<|Ŀ|>",
2279
+ "<|ŀ|>",
2280
+ "<|Ł|>",
2281
+ "<|ł|>",
2282
+ "<|Ń|>",
2283
+ "<|Ûķ|>",
2284
+ "<|ÛĮ|>",
2285
+ "<|ا|>",
2286
+ "<|ĠØ|>",
2287
+ "<|ÙĪ|>",
2288
+ "<|ÙĨ|>",
2289
+ "<|ر|>",
2290
+ "<|Ú©|>",
2291
+ "<|ĠÙ|>",
2292
+ "<|ت|>",
2293
+ "<|اÙĨ|>",
2294
+ "<|Ûİ|>",
2295
+ "<|د|>",
2296
+ "<|Ùħ|>",
2297
+ "<|Ġب|>",
2298
+ "<|ÛĨ|>",
2299
+ "<|س|>",
2300
+ "<|translate|>",
2301
+ "<|transcribe|>",
2302
+ "<|startoflm|>",
2303
+ "<|startofprev|>",
2304
+ "<|nocaptions|>",
2305
+ "<|notimestamps|>"
2306
+ ],
2307
+ "bos_token": "<|endoftext|>",
2308
+ "clean_up_tokenization_spaces": true,
2309
+ "cls_token": "[CLS]",
2310
+ "do_basic_tokenize": true,
2311
+ "do_lower_case": true,
2312
+ "eos_token": "<|endoftext|>",
2313
+ "errors": "replace",
2314
+ "mask_token": "[MASK]",
2315
+ "model_max_length": 1024,
2316
+ "never_split": null,
2317
+ "pad_token": "<|endoftext|>",
2318
+ "processor_class": "WhisperProcessor",
2319
+ "return_attention_mask": false,
2320
+ "sep_token": "[SEP]",
2321
+ "strip_accents": null,
2322
+ "tokenize_chinese_chars": true,
2323
+ "tokenizer_class": "BertTokenizer",
2324
+ "unk_token": "<|endoftext|>"
2325
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff