tsuyuan commited on
Commit
b18b906
·
1 Parent(s): d19b1f1

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +1026 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer_config.json +63 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "v_tok_0": 50265,
3
+ "v_tok_1": 50266,
4
+ "v_tok_10": 50275,
5
+ "v_tok_100": 50365,
6
+ "v_tok_1000": 51265,
7
+ "v_tok_1001": 51266,
8
+ "v_tok_1002": 51267,
9
+ "v_tok_1003": 51268,
10
+ "v_tok_1004": 51269,
11
+ "v_tok_1005": 51270,
12
+ "v_tok_1006": 51271,
13
+ "v_tok_1007": 51272,
14
+ "v_tok_1008": 51273,
15
+ "v_tok_1009": 51274,
16
+ "v_tok_101": 50366,
17
+ "v_tok_1010": 51275,
18
+ "v_tok_1011": 51276,
19
+ "v_tok_1012": 51277,
20
+ "v_tok_1013": 51278,
21
+ "v_tok_1014": 51279,
22
+ "v_tok_1015": 51280,
23
+ "v_tok_1016": 51281,
24
+ "v_tok_1017": 51282,
25
+ "v_tok_1018": 51283,
26
+ "v_tok_1019": 51284,
27
+ "v_tok_102": 50367,
28
+ "v_tok_1020": 51285,
29
+ "v_tok_1021": 51286,
30
+ "v_tok_1022": 51287,
31
+ "v_tok_1023": 51288,
32
+ "v_tok_103": 50368,
33
+ "v_tok_104": 50369,
34
+ "v_tok_105": 50370,
35
+ "v_tok_106": 50371,
36
+ "v_tok_107": 50372,
37
+ "v_tok_108": 50373,
38
+ "v_tok_109": 50374,
39
+ "v_tok_11": 50276,
40
+ "v_tok_110": 50375,
41
+ "v_tok_111": 50376,
42
+ "v_tok_112": 50377,
43
+ "v_tok_113": 50378,
44
+ "v_tok_114": 50379,
45
+ "v_tok_115": 50380,
46
+ "v_tok_116": 50381,
47
+ "v_tok_117": 50382,
48
+ "v_tok_118": 50383,
49
+ "v_tok_119": 50384,
50
+ "v_tok_12": 50277,
51
+ "v_tok_120": 50385,
52
+ "v_tok_121": 50386,
53
+ "v_tok_122": 50387,
54
+ "v_tok_123": 50388,
55
+ "v_tok_124": 50389,
56
+ "v_tok_125": 50390,
57
+ "v_tok_126": 50391,
58
+ "v_tok_127": 50392,
59
+ "v_tok_128": 50393,
60
+ "v_tok_129": 50394,
61
+ "v_tok_13": 50278,
62
+ "v_tok_130": 50395,
63
+ "v_tok_131": 50396,
64
+ "v_tok_132": 50397,
65
+ "v_tok_133": 50398,
66
+ "v_tok_134": 50399,
67
+ "v_tok_135": 50400,
68
+ "v_tok_136": 50401,
69
+ "v_tok_137": 50402,
70
+ "v_tok_138": 50403,
71
+ "v_tok_139": 50404,
72
+ "v_tok_14": 50279,
73
+ "v_tok_140": 50405,
74
+ "v_tok_141": 50406,
75
+ "v_tok_142": 50407,
76
+ "v_tok_143": 50408,
77
+ "v_tok_144": 50409,
78
+ "v_tok_145": 50410,
79
+ "v_tok_146": 50411,
80
+ "v_tok_147": 50412,
81
+ "v_tok_148": 50413,
82
+ "v_tok_149": 50414,
83
+ "v_tok_15": 50280,
84
+ "v_tok_150": 50415,
85
+ "v_tok_151": 50416,
86
+ "v_tok_152": 50417,
87
+ "v_tok_153": 50418,
88
+ "v_tok_154": 50419,
89
+ "v_tok_155": 50420,
90
+ "v_tok_156": 50421,
91
+ "v_tok_157": 50422,
92
+ "v_tok_158": 50423,
93
+ "v_tok_159": 50424,
94
+ "v_tok_16": 50281,
95
+ "v_tok_160": 50425,
96
+ "v_tok_161": 50426,
97
+ "v_tok_162": 50427,
98
+ "v_tok_163": 50428,
99
+ "v_tok_164": 50429,
100
+ "v_tok_165": 50430,
101
+ "v_tok_166": 50431,
102
+ "v_tok_167": 50432,
103
+ "v_tok_168": 50433,
104
+ "v_tok_169": 50434,
105
+ "v_tok_17": 50282,
106
+ "v_tok_170": 50435,
107
+ "v_tok_171": 50436,
108
+ "v_tok_172": 50437,
109
+ "v_tok_173": 50438,
110
+ "v_tok_174": 50439,
111
+ "v_tok_175": 50440,
112
+ "v_tok_176": 50441,
113
+ "v_tok_177": 50442,
114
+ "v_tok_178": 50443,
115
+ "v_tok_179": 50444,
116
+ "v_tok_18": 50283,
117
+ "v_tok_180": 50445,
118
+ "v_tok_181": 50446,
119
+ "v_tok_182": 50447,
120
+ "v_tok_183": 50448,
121
+ "v_tok_184": 50449,
122
+ "v_tok_185": 50450,
123
+ "v_tok_186": 50451,
124
+ "v_tok_187": 50452,
125
+ "v_tok_188": 50453,
126
+ "v_tok_189": 50454,
127
+ "v_tok_19": 50284,
128
+ "v_tok_190": 50455,
129
+ "v_tok_191": 50456,
130
+ "v_tok_192": 50457,
131
+ "v_tok_193": 50458,
132
+ "v_tok_194": 50459,
133
+ "v_tok_195": 50460,
134
+ "v_tok_196": 50461,
135
+ "v_tok_197": 50462,
136
+ "v_tok_198": 50463,
137
+ "v_tok_199": 50464,
138
+ "v_tok_2": 50267,
139
+ "v_tok_20": 50285,
140
+ "v_tok_200": 50465,
141
+ "v_tok_201": 50466,
142
+ "v_tok_202": 50467,
143
+ "v_tok_203": 50468,
144
+ "v_tok_204": 50469,
145
+ "v_tok_205": 50470,
146
+ "v_tok_206": 50471,
147
+ "v_tok_207": 50472,
148
+ "v_tok_208": 50473,
149
+ "v_tok_209": 50474,
150
+ "v_tok_21": 50286,
151
+ "v_tok_210": 50475,
152
+ "v_tok_211": 50476,
153
+ "v_tok_212": 50477,
154
+ "v_tok_213": 50478,
155
+ "v_tok_214": 50479,
156
+ "v_tok_215": 50480,
157
+ "v_tok_216": 50481,
158
+ "v_tok_217": 50482,
159
+ "v_tok_218": 50483,
160
+ "v_tok_219": 50484,
161
+ "v_tok_22": 50287,
162
+ "v_tok_220": 50485,
163
+ "v_tok_221": 50486,
164
+ "v_tok_222": 50487,
165
+ "v_tok_223": 50488,
166
+ "v_tok_224": 50489,
167
+ "v_tok_225": 50490,
168
+ "v_tok_226": 50491,
169
+ "v_tok_227": 50492,
170
+ "v_tok_228": 50493,
171
+ "v_tok_229": 50494,
172
+ "v_tok_23": 50288,
173
+ "v_tok_230": 50495,
174
+ "v_tok_231": 50496,
175
+ "v_tok_232": 50497,
176
+ "v_tok_233": 50498,
177
+ "v_tok_234": 50499,
178
+ "v_tok_235": 50500,
179
+ "v_tok_236": 50501,
180
+ "v_tok_237": 50502,
181
+ "v_tok_238": 50503,
182
+ "v_tok_239": 50504,
183
+ "v_tok_24": 50289,
184
+ "v_tok_240": 50505,
185
+ "v_tok_241": 50506,
186
+ "v_tok_242": 50507,
187
+ "v_tok_243": 50508,
188
+ "v_tok_244": 50509,
189
+ "v_tok_245": 50510,
190
+ "v_tok_246": 50511,
191
+ "v_tok_247": 50512,
192
+ "v_tok_248": 50513,
193
+ "v_tok_249": 50514,
194
+ "v_tok_25": 50290,
195
+ "v_tok_250": 50515,
196
+ "v_tok_251": 50516,
197
+ "v_tok_252": 50517,
198
+ "v_tok_253": 50518,
199
+ "v_tok_254": 50519,
200
+ "v_tok_255": 50520,
201
+ "v_tok_256": 50521,
202
+ "v_tok_257": 50522,
203
+ "v_tok_258": 50523,
204
+ "v_tok_259": 50524,
205
+ "v_tok_26": 50291,
206
+ "v_tok_260": 50525,
207
+ "v_tok_261": 50526,
208
+ "v_tok_262": 50527,
209
+ "v_tok_263": 50528,
210
+ "v_tok_264": 50529,
211
+ "v_tok_265": 50530,
212
+ "v_tok_266": 50531,
213
+ "v_tok_267": 50532,
214
+ "v_tok_268": 50533,
215
+ "v_tok_269": 50534,
216
+ "v_tok_27": 50292,
217
+ "v_tok_270": 50535,
218
+ "v_tok_271": 50536,
219
+ "v_tok_272": 50537,
220
+ "v_tok_273": 50538,
221
+ "v_tok_274": 50539,
222
+ "v_tok_275": 50540,
223
+ "v_tok_276": 50541,
224
+ "v_tok_277": 50542,
225
+ "v_tok_278": 50543,
226
+ "v_tok_279": 50544,
227
+ "v_tok_28": 50293,
228
+ "v_tok_280": 50545,
229
+ "v_tok_281": 50546,
230
+ "v_tok_282": 50547,
231
+ "v_tok_283": 50548,
232
+ "v_tok_284": 50549,
233
+ "v_tok_285": 50550,
234
+ "v_tok_286": 50551,
235
+ "v_tok_287": 50552,
236
+ "v_tok_288": 50553,
237
+ "v_tok_289": 50554,
238
+ "v_tok_29": 50294,
239
+ "v_tok_290": 50555,
240
+ "v_tok_291": 50556,
241
+ "v_tok_292": 50557,
242
+ "v_tok_293": 50558,
243
+ "v_tok_294": 50559,
244
+ "v_tok_295": 50560,
245
+ "v_tok_296": 50561,
246
+ "v_tok_297": 50562,
247
+ "v_tok_298": 50563,
248
+ "v_tok_299": 50564,
249
+ "v_tok_3": 50268,
250
+ "v_tok_30": 50295,
251
+ "v_tok_300": 50565,
252
+ "v_tok_301": 50566,
253
+ "v_tok_302": 50567,
254
+ "v_tok_303": 50568,
255
+ "v_tok_304": 50569,
256
+ "v_tok_305": 50570,
257
+ "v_tok_306": 50571,
258
+ "v_tok_307": 50572,
259
+ "v_tok_308": 50573,
260
+ "v_tok_309": 50574,
261
+ "v_tok_31": 50296,
262
+ "v_tok_310": 50575,
263
+ "v_tok_311": 50576,
264
+ "v_tok_312": 50577,
265
+ "v_tok_313": 50578,
266
+ "v_tok_314": 50579,
267
+ "v_tok_315": 50580,
268
+ "v_tok_316": 50581,
269
+ "v_tok_317": 50582,
270
+ "v_tok_318": 50583,
271
+ "v_tok_319": 50584,
272
+ "v_tok_32": 50297,
273
+ "v_tok_320": 50585,
274
+ "v_tok_321": 50586,
275
+ "v_tok_322": 50587,
276
+ "v_tok_323": 50588,
277
+ "v_tok_324": 50589,
278
+ "v_tok_325": 50590,
279
+ "v_tok_326": 50591,
280
+ "v_tok_327": 50592,
281
+ "v_tok_328": 50593,
282
+ "v_tok_329": 50594,
283
+ "v_tok_33": 50298,
284
+ "v_tok_330": 50595,
285
+ "v_tok_331": 50596,
286
+ "v_tok_332": 50597,
287
+ "v_tok_333": 50598,
288
+ "v_tok_334": 50599,
289
+ "v_tok_335": 50600,
290
+ "v_tok_336": 50601,
291
+ "v_tok_337": 50602,
292
+ "v_tok_338": 50603,
293
+ "v_tok_339": 50604,
294
+ "v_tok_34": 50299,
295
+ "v_tok_340": 50605,
296
+ "v_tok_341": 50606,
297
+ "v_tok_342": 50607,
298
+ "v_tok_343": 50608,
299
+ "v_tok_344": 50609,
300
+ "v_tok_345": 50610,
301
+ "v_tok_346": 50611,
302
+ "v_tok_347": 50612,
303
+ "v_tok_348": 50613,
304
+ "v_tok_349": 50614,
305
+ "v_tok_35": 50300,
306
+ "v_tok_350": 50615,
307
+ "v_tok_351": 50616,
308
+ "v_tok_352": 50617,
309
+ "v_tok_353": 50618,
310
+ "v_tok_354": 50619,
311
+ "v_tok_355": 50620,
312
+ "v_tok_356": 50621,
313
+ "v_tok_357": 50622,
314
+ "v_tok_358": 50623,
315
+ "v_tok_359": 50624,
316
+ "v_tok_36": 50301,
317
+ "v_tok_360": 50625,
318
+ "v_tok_361": 50626,
319
+ "v_tok_362": 50627,
320
+ "v_tok_363": 50628,
321
+ "v_tok_364": 50629,
322
+ "v_tok_365": 50630,
323
+ "v_tok_366": 50631,
324
+ "v_tok_367": 50632,
325
+ "v_tok_368": 50633,
326
+ "v_tok_369": 50634,
327
+ "v_tok_37": 50302,
328
+ "v_tok_370": 50635,
329
+ "v_tok_371": 50636,
330
+ "v_tok_372": 50637,
331
+ "v_tok_373": 50638,
332
+ "v_tok_374": 50639,
333
+ "v_tok_375": 50640,
334
+ "v_tok_376": 50641,
335
+ "v_tok_377": 50642,
336
+ "v_tok_378": 50643,
337
+ "v_tok_379": 50644,
338
+ "v_tok_38": 50303,
339
+ "v_tok_380": 50645,
340
+ "v_tok_381": 50646,
341
+ "v_tok_382": 50647,
342
+ "v_tok_383": 50648,
343
+ "v_tok_384": 50649,
344
+ "v_tok_385": 50650,
345
+ "v_tok_386": 50651,
346
+ "v_tok_387": 50652,
347
+ "v_tok_388": 50653,
348
+ "v_tok_389": 50654,
349
+ "v_tok_39": 50304,
350
+ "v_tok_390": 50655,
351
+ "v_tok_391": 50656,
352
+ "v_tok_392": 50657,
353
+ "v_tok_393": 50658,
354
+ "v_tok_394": 50659,
355
+ "v_tok_395": 50660,
356
+ "v_tok_396": 50661,
357
+ "v_tok_397": 50662,
358
+ "v_tok_398": 50663,
359
+ "v_tok_399": 50664,
360
+ "v_tok_4": 50269,
361
+ "v_tok_40": 50305,
362
+ "v_tok_400": 50665,
363
+ "v_tok_401": 50666,
364
+ "v_tok_402": 50667,
365
+ "v_tok_403": 50668,
366
+ "v_tok_404": 50669,
367
+ "v_tok_405": 50670,
368
+ "v_tok_406": 50671,
369
+ "v_tok_407": 50672,
370
+ "v_tok_408": 50673,
371
+ "v_tok_409": 50674,
372
+ "v_tok_41": 50306,
373
+ "v_tok_410": 50675,
374
+ "v_tok_411": 50676,
375
+ "v_tok_412": 50677,
376
+ "v_tok_413": 50678,
377
+ "v_tok_414": 50679,
378
+ "v_tok_415": 50680,
379
+ "v_tok_416": 50681,
380
+ "v_tok_417": 50682,
381
+ "v_tok_418": 50683,
382
+ "v_tok_419": 50684,
383
+ "v_tok_42": 50307,
384
+ "v_tok_420": 50685,
385
+ "v_tok_421": 50686,
386
+ "v_tok_422": 50687,
387
+ "v_tok_423": 50688,
388
+ "v_tok_424": 50689,
389
+ "v_tok_425": 50690,
390
+ "v_tok_426": 50691,
391
+ "v_tok_427": 50692,
392
+ "v_tok_428": 50693,
393
+ "v_tok_429": 50694,
394
+ "v_tok_43": 50308,
395
+ "v_tok_430": 50695,
396
+ "v_tok_431": 50696,
397
+ "v_tok_432": 50697,
398
+ "v_tok_433": 50698,
399
+ "v_tok_434": 50699,
400
+ "v_tok_435": 50700,
401
+ "v_tok_436": 50701,
402
+ "v_tok_437": 50702,
403
+ "v_tok_438": 50703,
404
+ "v_tok_439": 50704,
405
+ "v_tok_44": 50309,
406
+ "v_tok_440": 50705,
407
+ "v_tok_441": 50706,
408
+ "v_tok_442": 50707,
409
+ "v_tok_443": 50708,
410
+ "v_tok_444": 50709,
411
+ "v_tok_445": 50710,
412
+ "v_tok_446": 50711,
413
+ "v_tok_447": 50712,
414
+ "v_tok_448": 50713,
415
+ "v_tok_449": 50714,
416
+ "v_tok_45": 50310,
417
+ "v_tok_450": 50715,
418
+ "v_tok_451": 50716,
419
+ "v_tok_452": 50717,
420
+ "v_tok_453": 50718,
421
+ "v_tok_454": 50719,
422
+ "v_tok_455": 50720,
423
+ "v_tok_456": 50721,
424
+ "v_tok_457": 50722,
425
+ "v_tok_458": 50723,
426
+ "v_tok_459": 50724,
427
+ "v_tok_46": 50311,
428
+ "v_tok_460": 50725,
429
+ "v_tok_461": 50726,
430
+ "v_tok_462": 50727,
431
+ "v_tok_463": 50728,
432
+ "v_tok_464": 50729,
433
+ "v_tok_465": 50730,
434
+ "v_tok_466": 50731,
435
+ "v_tok_467": 50732,
436
+ "v_tok_468": 50733,
437
+ "v_tok_469": 50734,
438
+ "v_tok_47": 50312,
439
+ "v_tok_470": 50735,
440
+ "v_tok_471": 50736,
441
+ "v_tok_472": 50737,
442
+ "v_tok_473": 50738,
443
+ "v_tok_474": 50739,
444
+ "v_tok_475": 50740,
445
+ "v_tok_476": 50741,
446
+ "v_tok_477": 50742,
447
+ "v_tok_478": 50743,
448
+ "v_tok_479": 50744,
449
+ "v_tok_48": 50313,
450
+ "v_tok_480": 50745,
451
+ "v_tok_481": 50746,
452
+ "v_tok_482": 50747,
453
+ "v_tok_483": 50748,
454
+ "v_tok_484": 50749,
455
+ "v_tok_485": 50750,
456
+ "v_tok_486": 50751,
457
+ "v_tok_487": 50752,
458
+ "v_tok_488": 50753,
459
+ "v_tok_489": 50754,
460
+ "v_tok_49": 50314,
461
+ "v_tok_490": 50755,
462
+ "v_tok_491": 50756,
463
+ "v_tok_492": 50757,
464
+ "v_tok_493": 50758,
465
+ "v_tok_494": 50759,
466
+ "v_tok_495": 50760,
467
+ "v_tok_496": 50761,
468
+ "v_tok_497": 50762,
469
+ "v_tok_498": 50763,
470
+ "v_tok_499": 50764,
471
+ "v_tok_5": 50270,
472
+ "v_tok_50": 50315,
473
+ "v_tok_500": 50765,
474
+ "v_tok_501": 50766,
475
+ "v_tok_502": 50767,
476
+ "v_tok_503": 50768,
477
+ "v_tok_504": 50769,
478
+ "v_tok_505": 50770,
479
+ "v_tok_506": 50771,
480
+ "v_tok_507": 50772,
481
+ "v_tok_508": 50773,
482
+ "v_tok_509": 50774,
483
+ "v_tok_51": 50316,
484
+ "v_tok_510": 50775,
485
+ "v_tok_511": 50776,
486
+ "v_tok_512": 50777,
487
+ "v_tok_513": 50778,
488
+ "v_tok_514": 50779,
489
+ "v_tok_515": 50780,
490
+ "v_tok_516": 50781,
491
+ "v_tok_517": 50782,
492
+ "v_tok_518": 50783,
493
+ "v_tok_519": 50784,
494
+ "v_tok_52": 50317,
495
+ "v_tok_520": 50785,
496
+ "v_tok_521": 50786,
497
+ "v_tok_522": 50787,
498
+ "v_tok_523": 50788,
499
+ "v_tok_524": 50789,
500
+ "v_tok_525": 50790,
501
+ "v_tok_526": 50791,
502
+ "v_tok_527": 50792,
503
+ "v_tok_528": 50793,
504
+ "v_tok_529": 50794,
505
+ "v_tok_53": 50318,
506
+ "v_tok_530": 50795,
507
+ "v_tok_531": 50796,
508
+ "v_tok_532": 50797,
509
+ "v_tok_533": 50798,
510
+ "v_tok_534": 50799,
511
+ "v_tok_535": 50800,
512
+ "v_tok_536": 50801,
513
+ "v_tok_537": 50802,
514
+ "v_tok_538": 50803,
515
+ "v_tok_539": 50804,
516
+ "v_tok_54": 50319,
517
+ "v_tok_540": 50805,
518
+ "v_tok_541": 50806,
519
+ "v_tok_542": 50807,
520
+ "v_tok_543": 50808,
521
+ "v_tok_544": 50809,
522
+ "v_tok_545": 50810,
523
+ "v_tok_546": 50811,
524
+ "v_tok_547": 50812,
525
+ "v_tok_548": 50813,
526
+ "v_tok_549": 50814,
527
+ "v_tok_55": 50320,
528
+ "v_tok_550": 50815,
529
+ "v_tok_551": 50816,
530
+ "v_tok_552": 50817,
531
+ "v_tok_553": 50818,
532
+ "v_tok_554": 50819,
533
+ "v_tok_555": 50820,
534
+ "v_tok_556": 50821,
535
+ "v_tok_557": 50822,
536
+ "v_tok_558": 50823,
537
+ "v_tok_559": 50824,
538
+ "v_tok_56": 50321,
539
+ "v_tok_560": 50825,
540
+ "v_tok_561": 50826,
541
+ "v_tok_562": 50827,
542
+ "v_tok_563": 50828,
543
+ "v_tok_564": 50829,
544
+ "v_tok_565": 50830,
545
+ "v_tok_566": 50831,
546
+ "v_tok_567": 50832,
547
+ "v_tok_568": 50833,
548
+ "v_tok_569": 50834,
549
+ "v_tok_57": 50322,
550
+ "v_tok_570": 50835,
551
+ "v_tok_571": 50836,
552
+ "v_tok_572": 50837,
553
+ "v_tok_573": 50838,
554
+ "v_tok_574": 50839,
555
+ "v_tok_575": 50840,
556
+ "v_tok_576": 50841,
557
+ "v_tok_577": 50842,
558
+ "v_tok_578": 50843,
559
+ "v_tok_579": 50844,
560
+ "v_tok_58": 50323,
561
+ "v_tok_580": 50845,
562
+ "v_tok_581": 50846,
563
+ "v_tok_582": 50847,
564
+ "v_tok_583": 50848,
565
+ "v_tok_584": 50849,
566
+ "v_tok_585": 50850,
567
+ "v_tok_586": 50851,
568
+ "v_tok_587": 50852,
569
+ "v_tok_588": 50853,
570
+ "v_tok_589": 50854,
571
+ "v_tok_59": 50324,
572
+ "v_tok_590": 50855,
573
+ "v_tok_591": 50856,
574
+ "v_tok_592": 50857,
575
+ "v_tok_593": 50858,
576
+ "v_tok_594": 50859,
577
+ "v_tok_595": 50860,
578
+ "v_tok_596": 50861,
579
+ "v_tok_597": 50862,
580
+ "v_tok_598": 50863,
581
+ "v_tok_599": 50864,
582
+ "v_tok_6": 50271,
583
+ "v_tok_60": 50325,
584
+ "v_tok_600": 50865,
585
+ "v_tok_601": 50866,
586
+ "v_tok_602": 50867,
587
+ "v_tok_603": 50868,
588
+ "v_tok_604": 50869,
589
+ "v_tok_605": 50870,
590
+ "v_tok_606": 50871,
591
+ "v_tok_607": 50872,
592
+ "v_tok_608": 50873,
593
+ "v_tok_609": 50874,
594
+ "v_tok_61": 50326,
595
+ "v_tok_610": 50875,
596
+ "v_tok_611": 50876,
597
+ "v_tok_612": 50877,
598
+ "v_tok_613": 50878,
599
+ "v_tok_614": 50879,
600
+ "v_tok_615": 50880,
601
+ "v_tok_616": 50881,
602
+ "v_tok_617": 50882,
603
+ "v_tok_618": 50883,
604
+ "v_tok_619": 50884,
605
+ "v_tok_62": 50327,
606
+ "v_tok_620": 50885,
607
+ "v_tok_621": 50886,
608
+ "v_tok_622": 50887,
609
+ "v_tok_623": 50888,
610
+ "v_tok_624": 50889,
611
+ "v_tok_625": 50890,
612
+ "v_tok_626": 50891,
613
+ "v_tok_627": 50892,
614
+ "v_tok_628": 50893,
615
+ "v_tok_629": 50894,
616
+ "v_tok_63": 50328,
617
+ "v_tok_630": 50895,
618
+ "v_tok_631": 50896,
619
+ "v_tok_632": 50897,
620
+ "v_tok_633": 50898,
621
+ "v_tok_634": 50899,
622
+ "v_tok_635": 50900,
623
+ "v_tok_636": 50901,
624
+ "v_tok_637": 50902,
625
+ "v_tok_638": 50903,
626
+ "v_tok_639": 50904,
627
+ "v_tok_64": 50329,
628
+ "v_tok_640": 50905,
629
+ "v_tok_641": 50906,
630
+ "v_tok_642": 50907,
631
+ "v_tok_643": 50908,
632
+ "v_tok_644": 50909,
633
+ "v_tok_645": 50910,
634
+ "v_tok_646": 50911,
635
+ "v_tok_647": 50912,
636
+ "v_tok_648": 50913,
637
+ "v_tok_649": 50914,
638
+ "v_tok_65": 50330,
639
+ "v_tok_650": 50915,
640
+ "v_tok_651": 50916,
641
+ "v_tok_652": 50917,
642
+ "v_tok_653": 50918,
643
+ "v_tok_654": 50919,
644
+ "v_tok_655": 50920,
645
+ "v_tok_656": 50921,
646
+ "v_tok_657": 50922,
647
+ "v_tok_658": 50923,
648
+ "v_tok_659": 50924,
649
+ "v_tok_66": 50331,
650
+ "v_tok_660": 50925,
651
+ "v_tok_661": 50926,
652
+ "v_tok_662": 50927,
653
+ "v_tok_663": 50928,
654
+ "v_tok_664": 50929,
655
+ "v_tok_665": 50930,
656
+ "v_tok_666": 50931,
657
+ "v_tok_667": 50932,
658
+ "v_tok_668": 50933,
659
+ "v_tok_669": 50934,
660
+ "v_tok_67": 50332,
661
+ "v_tok_670": 50935,
662
+ "v_tok_671": 50936,
663
+ "v_tok_672": 50937,
664
+ "v_tok_673": 50938,
665
+ "v_tok_674": 50939,
666
+ "v_tok_675": 50940,
667
+ "v_tok_676": 50941,
668
+ "v_tok_677": 50942,
669
+ "v_tok_678": 50943,
670
+ "v_tok_679": 50944,
671
+ "v_tok_68": 50333,
672
+ "v_tok_680": 50945,
673
+ "v_tok_681": 50946,
674
+ "v_tok_682": 50947,
675
+ "v_tok_683": 50948,
676
+ "v_tok_684": 50949,
677
+ "v_tok_685": 50950,
678
+ "v_tok_686": 50951,
679
+ "v_tok_687": 50952,
680
+ "v_tok_688": 50953,
681
+ "v_tok_689": 50954,
682
+ "v_tok_69": 50334,
683
+ "v_tok_690": 50955,
684
+ "v_tok_691": 50956,
685
+ "v_tok_692": 50957,
686
+ "v_tok_693": 50958,
687
+ "v_tok_694": 50959,
688
+ "v_tok_695": 50960,
689
+ "v_tok_696": 50961,
690
+ "v_tok_697": 50962,
691
+ "v_tok_698": 50963,
692
+ "v_tok_699": 50964,
693
+ "v_tok_7": 50272,
694
+ "v_tok_70": 50335,
695
+ "v_tok_700": 50965,
696
+ "v_tok_701": 50966,
697
+ "v_tok_702": 50967,
698
+ "v_tok_703": 50968,
699
+ "v_tok_704": 50969,
700
+ "v_tok_705": 50970,
701
+ "v_tok_706": 50971,
702
+ "v_tok_707": 50972,
703
+ "v_tok_708": 50973,
704
+ "v_tok_709": 50974,
705
+ "v_tok_71": 50336,
706
+ "v_tok_710": 50975,
707
+ "v_tok_711": 50976,
708
+ "v_tok_712": 50977,
709
+ "v_tok_713": 50978,
710
+ "v_tok_714": 50979,
711
+ "v_tok_715": 50980,
712
+ "v_tok_716": 50981,
713
+ "v_tok_717": 50982,
714
+ "v_tok_718": 50983,
715
+ "v_tok_719": 50984,
716
+ "v_tok_72": 50337,
717
+ "v_tok_720": 50985,
718
+ "v_tok_721": 50986,
719
+ "v_tok_722": 50987,
720
+ "v_tok_723": 50988,
721
+ "v_tok_724": 50989,
722
+ "v_tok_725": 50990,
723
+ "v_tok_726": 50991,
724
+ "v_tok_727": 50992,
725
+ "v_tok_728": 50993,
726
+ "v_tok_729": 50994,
727
+ "v_tok_73": 50338,
728
+ "v_tok_730": 50995,
729
+ "v_tok_731": 50996,
730
+ "v_tok_732": 50997,
731
+ "v_tok_733": 50998,
732
+ "v_tok_734": 50999,
733
+ "v_tok_735": 51000,
734
+ "v_tok_736": 51001,
735
+ "v_tok_737": 51002,
736
+ "v_tok_738": 51003,
737
+ "v_tok_739": 51004,
738
+ "v_tok_74": 50339,
739
+ "v_tok_740": 51005,
740
+ "v_tok_741": 51006,
741
+ "v_tok_742": 51007,
742
+ "v_tok_743": 51008,
743
+ "v_tok_744": 51009,
744
+ "v_tok_745": 51010,
745
+ "v_tok_746": 51011,
746
+ "v_tok_747": 51012,
747
+ "v_tok_748": 51013,
748
+ "v_tok_749": 51014,
749
+ "v_tok_75": 50340,
750
+ "v_tok_750": 51015,
751
+ "v_tok_751": 51016,
752
+ "v_tok_752": 51017,
753
+ "v_tok_753": 51018,
754
+ "v_tok_754": 51019,
755
+ "v_tok_755": 51020,
756
+ "v_tok_756": 51021,
757
+ "v_tok_757": 51022,
758
+ "v_tok_758": 51023,
759
+ "v_tok_759": 51024,
760
+ "v_tok_76": 50341,
761
+ "v_tok_760": 51025,
762
+ "v_tok_761": 51026,
763
+ "v_tok_762": 51027,
764
+ "v_tok_763": 51028,
765
+ "v_tok_764": 51029,
766
+ "v_tok_765": 51030,
767
+ "v_tok_766": 51031,
768
+ "v_tok_767": 51032,
769
+ "v_tok_768": 51033,
770
+ "v_tok_769": 51034,
771
+ "v_tok_77": 50342,
772
+ "v_tok_770": 51035,
773
+ "v_tok_771": 51036,
774
+ "v_tok_772": 51037,
775
+ "v_tok_773": 51038,
776
+ "v_tok_774": 51039,
777
+ "v_tok_775": 51040,
778
+ "v_tok_776": 51041,
779
+ "v_tok_777": 51042,
780
+ "v_tok_778": 51043,
781
+ "v_tok_779": 51044,
782
+ "v_tok_78": 50343,
783
+ "v_tok_780": 51045,
784
+ "v_tok_781": 51046,
785
+ "v_tok_782": 51047,
786
+ "v_tok_783": 51048,
787
+ "v_tok_784": 51049,
788
+ "v_tok_785": 51050,
789
+ "v_tok_786": 51051,
790
+ "v_tok_787": 51052,
791
+ "v_tok_788": 51053,
792
+ "v_tok_789": 51054,
793
+ "v_tok_79": 50344,
794
+ "v_tok_790": 51055,
795
+ "v_tok_791": 51056,
796
+ "v_tok_792": 51057,
797
+ "v_tok_793": 51058,
798
+ "v_tok_794": 51059,
799
+ "v_tok_795": 51060,
800
+ "v_tok_796": 51061,
801
+ "v_tok_797": 51062,
802
+ "v_tok_798": 51063,
803
+ "v_tok_799": 51064,
804
+ "v_tok_8": 50273,
805
+ "v_tok_80": 50345,
806
+ "v_tok_800": 51065,
807
+ "v_tok_801": 51066,
808
+ "v_tok_802": 51067,
809
+ "v_tok_803": 51068,
810
+ "v_tok_804": 51069,
811
+ "v_tok_805": 51070,
812
+ "v_tok_806": 51071,
813
+ "v_tok_807": 51072,
814
+ "v_tok_808": 51073,
815
+ "v_tok_809": 51074,
816
+ "v_tok_81": 50346,
817
+ "v_tok_810": 51075,
818
+ "v_tok_811": 51076,
819
+ "v_tok_812": 51077,
820
+ "v_tok_813": 51078,
821
+ "v_tok_814": 51079,
822
+ "v_tok_815": 51080,
823
+ "v_tok_816": 51081,
824
+ "v_tok_817": 51082,
825
+ "v_tok_818": 51083,
826
+ "v_tok_819": 51084,
827
+ "v_tok_82": 50347,
828
+ "v_tok_820": 51085,
829
+ "v_tok_821": 51086,
830
+ "v_tok_822": 51087,
831
+ "v_tok_823": 51088,
832
+ "v_tok_824": 51089,
833
+ "v_tok_825": 51090,
834
+ "v_tok_826": 51091,
835
+ "v_tok_827": 51092,
836
+ "v_tok_828": 51093,
837
+ "v_tok_829": 51094,
838
+ "v_tok_83": 50348,
839
+ "v_tok_830": 51095,
840
+ "v_tok_831": 51096,
841
+ "v_tok_832": 51097,
842
+ "v_tok_833": 51098,
843
+ "v_tok_834": 51099,
844
+ "v_tok_835": 51100,
845
+ "v_tok_836": 51101,
846
+ "v_tok_837": 51102,
847
+ "v_tok_838": 51103,
848
+ "v_tok_839": 51104,
849
+ "v_tok_84": 50349,
850
+ "v_tok_840": 51105,
851
+ "v_tok_841": 51106,
852
+ "v_tok_842": 51107,
853
+ "v_tok_843": 51108,
854
+ "v_tok_844": 51109,
855
+ "v_tok_845": 51110,
856
+ "v_tok_846": 51111,
857
+ "v_tok_847": 51112,
858
+ "v_tok_848": 51113,
859
+ "v_tok_849": 51114,
860
+ "v_tok_85": 50350,
861
+ "v_tok_850": 51115,
862
+ "v_tok_851": 51116,
863
+ "v_tok_852": 51117,
864
+ "v_tok_853": 51118,
865
+ "v_tok_854": 51119,
866
+ "v_tok_855": 51120,
867
+ "v_tok_856": 51121,
868
+ "v_tok_857": 51122,
869
+ "v_tok_858": 51123,
870
+ "v_tok_859": 51124,
871
+ "v_tok_86": 50351,
872
+ "v_tok_860": 51125,
873
+ "v_tok_861": 51126,
874
+ "v_tok_862": 51127,
875
+ "v_tok_863": 51128,
876
+ "v_tok_864": 51129,
877
+ "v_tok_865": 51130,
878
+ "v_tok_866": 51131,
879
+ "v_tok_867": 51132,
880
+ "v_tok_868": 51133,
881
+ "v_tok_869": 51134,
882
+ "v_tok_87": 50352,
883
+ "v_tok_870": 51135,
884
+ "v_tok_871": 51136,
885
+ "v_tok_872": 51137,
886
+ "v_tok_873": 51138,
887
+ "v_tok_874": 51139,
888
+ "v_tok_875": 51140,
889
+ "v_tok_876": 51141,
890
+ "v_tok_877": 51142,
891
+ "v_tok_878": 51143,
892
+ "v_tok_879": 51144,
893
+ "v_tok_88": 50353,
894
+ "v_tok_880": 51145,
895
+ "v_tok_881": 51146,
896
+ "v_tok_882": 51147,
897
+ "v_tok_883": 51148,
898
+ "v_tok_884": 51149,
899
+ "v_tok_885": 51150,
900
+ "v_tok_886": 51151,
901
+ "v_tok_887": 51152,
902
+ "v_tok_888": 51153,
903
+ "v_tok_889": 51154,
904
+ "v_tok_89": 50354,
905
+ "v_tok_890": 51155,
906
+ "v_tok_891": 51156,
907
+ "v_tok_892": 51157,
908
+ "v_tok_893": 51158,
909
+ "v_tok_894": 51159,
910
+ "v_tok_895": 51160,
911
+ "v_tok_896": 51161,
912
+ "v_tok_897": 51162,
913
+ "v_tok_898": 51163,
914
+ "v_tok_899": 51164,
915
+ "v_tok_9": 50274,
916
+ "v_tok_90": 50355,
917
+ "v_tok_900": 51165,
918
+ "v_tok_901": 51166,
919
+ "v_tok_902": 51167,
920
+ "v_tok_903": 51168,
921
+ "v_tok_904": 51169,
922
+ "v_tok_905": 51170,
923
+ "v_tok_906": 51171,
924
+ "v_tok_907": 51172,
925
+ "v_tok_908": 51173,
926
+ "v_tok_909": 51174,
927
+ "v_tok_91": 50356,
928
+ "v_tok_910": 51175,
929
+ "v_tok_911": 51176,
930
+ "v_tok_912": 51177,
931
+ "v_tok_913": 51178,
932
+ "v_tok_914": 51179,
933
+ "v_tok_915": 51180,
934
+ "v_tok_916": 51181,
935
+ "v_tok_917": 51182,
936
+ "v_tok_918": 51183,
937
+ "v_tok_919": 51184,
938
+ "v_tok_92": 50357,
939
+ "v_tok_920": 51185,
940
+ "v_tok_921": 51186,
941
+ "v_tok_922": 51187,
942
+ "v_tok_923": 51188,
943
+ "v_tok_924": 51189,
944
+ "v_tok_925": 51190,
945
+ "v_tok_926": 51191,
946
+ "v_tok_927": 51192,
947
+ "v_tok_928": 51193,
948
+ "v_tok_929": 51194,
949
+ "v_tok_93": 50358,
950
+ "v_tok_930": 51195,
951
+ "v_tok_931": 51196,
952
+ "v_tok_932": 51197,
953
+ "v_tok_933": 51198,
954
+ "v_tok_934": 51199,
955
+ "v_tok_935": 51200,
956
+ "v_tok_936": 51201,
957
+ "v_tok_937": 51202,
958
+ "v_tok_938": 51203,
959
+ "v_tok_939": 51204,
960
+ "v_tok_94": 50359,
961
+ "v_tok_940": 51205,
962
+ "v_tok_941": 51206,
963
+ "v_tok_942": 51207,
964
+ "v_tok_943": 51208,
965
+ "v_tok_944": 51209,
966
+ "v_tok_945": 51210,
967
+ "v_tok_946": 51211,
968
+ "v_tok_947": 51212,
969
+ "v_tok_948": 51213,
970
+ "v_tok_949": 51214,
971
+ "v_tok_95": 50360,
972
+ "v_tok_950": 51215,
973
+ "v_tok_951": 51216,
974
+ "v_tok_952": 51217,
975
+ "v_tok_953": 51218,
976
+ "v_tok_954": 51219,
977
+ "v_tok_955": 51220,
978
+ "v_tok_956": 51221,
979
+ "v_tok_957": 51222,
980
+ "v_tok_958": 51223,
981
+ "v_tok_959": 51224,
982
+ "v_tok_96": 50361,
983
+ "v_tok_960": 51225,
984
+ "v_tok_961": 51226,
985
+ "v_tok_962": 51227,
986
+ "v_tok_963": 51228,
987
+ "v_tok_964": 51229,
988
+ "v_tok_965": 51230,
989
+ "v_tok_966": 51231,
990
+ "v_tok_967": 51232,
991
+ "v_tok_968": 51233,
992
+ "v_tok_969": 51234,
993
+ "v_tok_97": 50362,
994
+ "v_tok_970": 51235,
995
+ "v_tok_971": 51236,
996
+ "v_tok_972": 51237,
997
+ "v_tok_973": 51238,
998
+ "v_tok_974": 51239,
999
+ "v_tok_975": 51240,
1000
+ "v_tok_976": 51241,
1001
+ "v_tok_977": 51242,
1002
+ "v_tok_978": 51243,
1003
+ "v_tok_979": 51244,
1004
+ "v_tok_98": 50363,
1005
+ "v_tok_980": 51245,
1006
+ "v_tok_981": 51246,
1007
+ "v_tok_982": 51247,
1008
+ "v_tok_983": 51248,
1009
+ "v_tok_984": 51249,
1010
+ "v_tok_985": 51250,
1011
+ "v_tok_986": 51251,
1012
+ "v_tok_987": 51252,
1013
+ "v_tok_988": 51253,
1014
+ "v_tok_989": 51254,
1015
+ "v_tok_99": 50364,
1016
+ "v_tok_990": 51255,
1017
+ "v_tok_991": 51256,
1018
+ "v_tok_992": 51257,
1019
+ "v_tok_993": 51258,
1020
+ "v_tok_994": 51259,
1021
+ "v_tok_995": 51260,
1022
+ "v_tok_996": 51261,
1023
+ "v_tok_997": 51262,
1024
+ "v_tok_998": 51263,
1025
+ "v_tok_999": 51264
1026
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 1024,
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "special_tokens_map_file": null,
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": {
56
+ "__type": "AddedToken",
57
+ "content": "<unk>",
58
+ "lstrip": false,
59
+ "normalized": true,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ }
63
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff