Hugging Face's logo

aixk
/
FS-2

Model card Files
xet
 Community
aixk commited on
Commit
dd3ac40
·
verified ·
1 Parent(s): a3dd33c

Upload fs2_bpe_model.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. fs2_bpe_model.json +1123 -0
fs2_bpe_model.json ADDED
@@ -0,0 +1,1123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<unk>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<bos>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<eos>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Metaspace",
46
+ "replacement": " ",
47
+ "prepend_scheme": "always",
48
+ "split": true
49
+ },
50
+ "post_processor": null,
51
+ "decoder": {
52
+ "type": "Metaspace",
53
+ "replacement": " ",
54
+ "prepend_scheme": "always",
55
+ "split": true
56
+ },
57
+ "model": {
58
+ "type": "BPE",
59
+ "dropout": null,
60
+ "unk_token": "<unk>",
61
+ "continuing_subword_prefix": null,
62
+ "end_of_word_suffix": null,
63
+ "fuse_unk": false,
64
+ "byte_fallback": false,
65
+ "ignore_merges": false,
66
+ "vocab": {
67
+ "<pad>": 0,
68
+ "<unk>": 1,
69
+ "<bos>": 2,
70
+ "<eos>": 3,
71
+ " ": 4,
72
+ "!": 5,
73
+ "\"": 6,
74
+ "#": 7,
75
+ "$": 8,
76
+ "%": 9,
77
+ "&": 10,
78
+ "'": 11,
79
+ "(": 12,
80
+ ")": 13,
81
+ "*": 14,
82
+ "+": 15,
83
+ ",": 16,
84
+ "-": 17,
85
+ ".": 18,
86
+ "/": 19,
87
+ "0": 20,
88
+ "1": 21,
89
+ "2": 22,
90
+ "3": 23,
91
+ "4": 24,
92
+ "5": 25,
93
+ "6": 26,
94
+ "7": 27,
95
+ "8": 28,
96
+ "9": 29,
97
+ ":": 30,
98
+ ";": 31,
99
+ "<": 32,
100
+ "=": 33,
101
+ ">": 34,
102
+ "?": 35,
103
+ "@": 36,
104
+ "A": 37,
105
+ "B": 38,
106
+ "C": 39,
107
+ "D": 40,
108
+ "E": 41,
109
+ "F": 42,
110
+ "G": 43,
111
+ "H": 44,
112
+ "I": 45,
113
+ "J": 46,
114
+ "K": 47,
115
+ "L": 48,
116
+ "M": 49,
117
+ "N": 50,
118
+ "O": 51,
119
+ "P": 52,
120
+ "Q": 53,
121
+ "R": 54,
122
+ "S": 55,
123
+ "T": 56,
124
+ "U": 57,
125
+ "V": 58,
126
+ "W": 59,
127
+ "X": 60,
128
+ "Y": 61,
129
+ "Z": 62,
130
+ "[": 63,
131
+ "\\": 64,
132
+ "]": 65,
133
+ "^": 66,
134
+ "_": 67,
135
+ "`": 68,
136
+ "a": 69,
137
+ "b": 70,
138
+ "c": 71,
139
+ "d": 72,
140
+ "e": 73,
141
+ "f": 74,
142
+ "g": 75,
143
+ "h": 76,
144
+ "i": 77,
145
+ "j": 78,
146
+ "k": 79,
147
+ "l": 80,
148
+ "m": 81,
149
+ "n": 82,
150
+ "o": 83,
151
+ "p": 84,
152
+ "q": 85,
153
+ "r": 86,
154
+ "s": 87,
155
+ "t": 88,
156
+ "u": 89,
157
+ "v": 90,
158
+ "w": 91,
159
+ "x": 92,
160
+ "y": 93,
161
+ "z": 94,
162
+ "{": 95,
163
+ "|": 96,
164
+ "}": 97,
165
+ "~": 98,
166
+ "¡": 99,
167
+ "¢": 100,
168
+ "£": 101,
169
+ "¤": 102,
170
+ "¥": 103,
171
+ "¦": 104,
172
+ "§": 105,
173
+ "¨": 106,
174
+ "©": 107,
175
+ "ª": 108,
176
+ "«": 109,
177
+ "¬": 110,
178
+ "®": 111,
179
+ "¯": 112,
180
+ "°": 113,
181
+ "±": 114,
182
+ "²": 115,
183
+ "³": 116,
184
+ "´": 117,
185
+ "µ": 118,
186
+ "¶": 119,
187
+ "·": 120,
188
+ "¸": 121,
189
+ "¹": 122,
190
+ "º": 123,
191
+ "»": 124,
192
+ "¼": 125,
193
+ "½": 126,
194
+ "¾": 127,
195
+ "¿": 128,
196
+ "À": 129,
197
+ "Á": 130,
198
+ "Â": 131,
199
+ "Ã": 132,
200
+ "Ä": 133,
201
+ "Å": 134,
202
+ "Æ": 135,
203
+ "Ç": 136,
204
+ "È": 137,
205
+ "É": 138,
206
+ "Ê": 139,
207
+ "Ë": 140,
208
+ "Ì": 141,
209
+ "Í": 142,
210
+ "Î": 143,
211
+ "Ï": 144,
212
+ "Ð": 145,
213
+ "Ñ": 146,
214
+ "Ò": 147,
215
+ "Ó": 148,
216
+ "Ô": 149,
217
+ "Õ": 150,
218
+ "Ö": 151,
219
+ "×": 152,
220
+ "Ø": 153,
221
+ "Ù": 154,
222
+ "Ú": 155,
223
+ "Û": 156,
224
+ "Ü": 157,
225
+ "Ý": 158,
226
+ "Þ": 159,
227
+ "ß": 160,
228
+ "à": 161,
229
+ "á": 162,
230
+ "â": 163,
231
+ "ã": 164,
232
+ "ä": 165,
233
+ "å": 166,
234
+ "æ": 167,
235
+ "ç": 168,
236
+ "è": 169,
237
+ "é": 170,
238
+ "ê": 171,
239
+ "ë": 172,
240
+ "ì": 173,
241
+ "í": 174,
242
+ "î": 175,
243
+ "ï": 176,
244
+ "ð": 177,
245
+ "ñ": 178,
246
+ "ò": 179,
247
+ "ó": 180,
248
+ "ô": 181,
249
+ "õ": 182,
250
+ "ö": 183,
251
+ "÷": 184,
252
+ "ø": 185,
253
+ "ù": 186,
254
+ "ú": 187,
255
+ "û": 188,
256
+ "ü": 189,
257
+ "ý": 190,
258
+ "þ": 191,
259
+ "ÿ": 192,
260
+ "Ā": 193,
261
+ "ā": 194,
262
+ "Ă": 195,
263
+ "ă": 196,
264
+ "Ą": 197,
265
+ "ą": 198,
266
+ "Ć": 199,
267
+ "ć": 200,
268
+ "Ĉ": 201,
269
+ "ĉ": 202,
270
+ "Ċ": 203,
271
+ "ċ": 204,
272
+ "Č": 205,
273
+ "č": 206,
274
+ "Ď": 207,
275
+ "ď": 208,
276
+ "Đ": 209,
277
+ "đ": 210,
278
+ "Ē": 211,
279
+ "ē": 212,
280
+ "Ĕ": 213,
281
+ "ĕ": 214,
282
+ "Ė": 215,
283
+ "ė": 216,
284
+ "Ę": 217,
285
+ "ę": 218,
286
+ "Ě": 219,
287
+ "ě": 220,
288
+ "Ĝ": 221,
289
+ "ĝ": 222,
290
+ "Ğ": 223,
291
+ "ğ": 224,
292
+ "Ġ": 225,
293
+ "ġ": 226,
294
+ "Ģ": 227,
295
+ "ģ": 228,
296
+ "Ĥ": 229,
297
+ "ĥ": 230,
298
+ "Ħ": 231,
299
+ "ħ": 232,
300
+ "Ĩ": 233,
301
+ "ĩ": 234,
302
+ "Ī": 235,
303
+ "ī": 236,
304
+ "Ĭ": 237,
305
+ "ĭ": 238,
306
+ "Į": 239,
307
+ "į": 240,
308
+ "İ": 241,
309
+ "ı": 242,
310
+ "IJ": 243,
311
+ "ij": 244,
312
+ "Ĵ": 245,
313
+ "ĵ": 246,
314
+ "Ķ": 247,
315
+ "ķ": 248,
316
+ "ĸ": 249,
317
+ "Ĺ": 250,
318
+ "ĺ": 251,
319
+ "Ļ": 252,
320
+ "ļ": 253,
321
+ "Ľ": 254,
322
+ "ľ": 255,
323
+ "Ŀ": 256,
324
+ "ŀ": 257,
325
+ "Ł": 258,
326
+ "ł": 259,
327
+ "Ń": 260,
328
+ "、": 261,
329
+ "。": 262,
330
+ "あ": 263,
331
+ "い": 264,
332
+ "が": 265,
333
+ "し": 266,
334
+ "す": 267,
335
+ "て": 268,
336
+ "で": 269,
337
+ "に": 270,
338
+ "の": 271,
339
+ "は": 272,
340
+ "ま": 273,
341
+ "り": 274,
342
+ "世": 275,
343
+ "习": 276,
344
+ "京": 277,
345
+ "人": 278,
346
+ "処": 279,
347
+ "变": 280,
348
+ "和": 281,
349
+ "在": 282,
350
+ "型": 283,
351
+ "学": 284,
352
+ "局": 285,
353
+ "展": 286,
354
+ "工": 287,
355
+ "度": 288,
356
+ "急": 289,
357
+ "技": 290,
358
+ "改": 291,
359
+ "日": 292,
360
+ "智": 293,
361
+ "本": 294,
362
+ "术": 295,
363
+ "東": 296,
364
+ "格": 297,
365
+ "模": 298,
366
+ "正": 299,
367
+ "深": 300,
368
+ "然": 301,
369
+ "理": 302,
370
+ "界": 303,
371
+ "的": 304,
372
+ "能": 305,
373
+ "自": 306,
374
+ "言": 307,
375
+ "語": 308,
376
+ "速": 309,
377
+ "進": 310,
378
+ "都": 311,
379
+ "首": 312,
380
+ "게": 313,
381
+ "고": 314,
382
+ "공": 315,
383
+ "국": 316,
384
+ "기": 317,
385
+ "는": 318,
386
+ "능": 319,
387
+ "니": 320,
388
+ "다": 321,
389
+ "대": 322,
390
+ "도": 323,
391
+ "르": 324,
392
+ "며": 325,
393
+ "민": 326,
394
+ "발": 327,
395
+ "빠": 328,
396
+ "서": 329,
397
+ "수": 330,
398
+ "술": 331,
399
+ "습": 332,
400
+ "울": 333,
401
+ "의": 334,
402
+ "이": 335,
403
+ "인": 336,
404
+ "있": 337,
405
+ "전": 338,
406
+ "지": 339,
407
+ "하": 340,
408
+ "한": 341,
409
+ "in": 342,
410
+ "ti": 343,
411
+ " a": 344,
412
+ "on": 345,
413
+ "re": 346,
414
+ "ing": 347,
415
+ "tion": 348,
416
+ " A": 349,
417
+ " c": 350,
418
+ " d": 351,
419
+ " l": 352,
420
+ " 人": 353,
421
+ " 日": 354,
422
+ " 기": 355,
423
+ " 대": 356,
424
+ " 발": 357,
425
+ " 빠": 358,
426
+ " 서": 359,
427
+ " 수": 360,
428
+ " 인": 361,
429
+ " 있": 362,
430
+ " in": 363,
431
+ " re": 364,
432
+ "al": 365,
433
+ "ar": 366,
434
+ "ation": 367,
435
+ "ce": 368,
436
+ "ci": 369,
437
+ "ee": 370,
438
+ "el": 371,
439
+ "en": 372,
440
+ "ear": 373,
441
+ "fi": 374,
442
+ "gen": 375,
443
+ "iz": 376,
444
+ "igen": 377,
445
+ "lu": 378,
446
+ "ligen": 379,
447
+ "mp": 380,
448
+ "nd": 381,
449
+ "ning": 382,
450
+ "olu": 383,
451
+ "omp": 384,
452
+ "rti": 385,
453
+ "tation": 386,
454
+ "tel": 387,
455
+ "utation": 388,
456
+ "volu": 389,
457
+ "、自": 390,
458
+ "あり": 391,
459
+ "いま": 392,
460
+ "が急": 393,
461
+ "して": 394,
462
+ "す。": 395,
463
+ "であり": 396,
464
+ "に進": 397,
465
+ "の首": 398,
466
+ "は東": 399,
467
+ "世界": 400,
468
+ "习模": 401,
469
+ "京であり": 402,
470
+ "処理": 403,
471
+ "变世界": 404,
472
+ "和深": 405,
473
+ "在改": 406,
474
+ "型正": 407,
475
+ "学习模": 408,
476
+ "局。": 409,
477
+ "展して": 410,
478
+ "工智": 411,
479
+ "度学习模": 412,
480
+ "技术": 413,
481
+ "本の首": 414,
482
+ "格局。": 415,
483
+ "然言": 416,
484
+ "的技术": 417,
485
+ "能和深": 418,
486
+ "語処理": 419,
487
+ "速に進": 420,
488
+ "都は東": 421,
489
+ "공지": 422,
490
+ "국의": 423,
491
+ "니다": 424,
492
+ "도는": 425,
493
+ "르게": 426,
494
+ "민국의": 427,
495
+ "술이": 428,
496
+ "습니다": 429,
497
+ "울이": 430,
498
+ "전하": 431,
499
+ "한민국의": 432,
500
+ " are": 433,
501
+ " and": 434,
502
+ "tioniz": 435,
503
+ " Arti": 436,
504
+ " comp": 437,
505
+ " dee": 438,
506
+ " lear": 439,
507
+ " 人工智": 440,
508
+ " 日本の首": 441,
509
+ " 기술이": 442,
510
+ " 대한민국의": 443,
511
+ " 발전하": 444,
512
+ " 빠르게": 445,
513
+ " 서울이": 446,
514
+ " 수도는": 447,
515
+ " 인공지": 448,
516
+ " 있습니다": 449,
517
+ " intel": 450,
518
+ " revolu": 451,
519
+ "cial": 452,
520
+ "ficial": 453,
521
+ "ligence": 454,
522
+ "utation.": 455,
523
+ "、自然言": 456,
524
+ "います。": 457,
525
+ "が急速に進": 458,
526
+ "京であり、自然言": 459,
527
+ "变世界的技术": 460,
528
+ "在改变世界的技术": 461,
529
+ "型正在改变世界的技术": 462,
530
+ "展しています。": 463,
531
+ "度学习模型���在改变世界的技术": 464,
532
+ "能和深度学习模型正在改变世界的技术": 465,
533
+ "語処理が急速に進": 466,
534
+ "都は東京であり、自然言": 467,
535
+ "tionizing": 468,
536
+ " Artificial": 469,
537
+ " computation.": 470,
538
+ " deep": 471,
539
+ " learning": 472,
540
+ " 人工智能和深度学习模型正在改变世界的技术": 473,
541
+ " 日本の首都は東京であり、自然言": 474,
542
+ " 발전하고": 475,
543
+ " 서울이며": 476,
544
+ " 인공지능": 477,
545
+ " 있습니다.": 478,
546
+ " intelligence": 479,
547
+ " revolutionizing": 480,
548
+ "語処理が急速に進展しています。": 481,
549
+ " 人工智能和深度学习模型正在改变世界的技术格局。": 482,
550
+ " 日本の首都は東京であり、自然言語処理が急速に進展しています。": 483
551
+ },
552
+ "merges": [
553
+ [
554
+ "i",
555
+ "n"
556
+ ],
557
+ [
558
+ "t",
559
+ "i"
560
+ ],
561
+ [
562
+ " ",
563
+ "a"
564
+ ],
565
+ [
566
+ "o",
567
+ "n"
568
+ ],
569
+ [
570
+ "r",
571
+ "e"
572
+ ],
573
+ [
574
+ "in",
575
+ "g"
576
+ ],
577
+ [
578
+ "ti",
579
+ "on"
580
+ ],
581
+ [
582
+ " ",
583
+ "A"
584
+ ],
585
+ [
586
+ " ",
587
+ "c"
588
+ ],
589
+ [
590
+ " ",
591
+ "d"
592
+ ],
593
+ [
594
+ " ",
595
+ "l"
596
+ ],
597
+ [
598
+ " ",
599
+ "人"
600
+ ],
601
+ [
602
+ " ",
603
+ "日"
604
+ ],
605
+ [
606
+ " ",
607
+ "기"
608
+ ],
609
+ [
610
+ " ",
611
+ "대"
612
+ ],
613
+ [
614
+ " ",
615
+ "발"
616
+ ],
617
+ [
618
+ " ",
619
+ "빠"
620
+ ],
621
+ [
622
+ " ",
623
+ "서"
624
+ ],
625
+ [
626
+ " ",
627
+ "수"
628
+ ],
629
+ [
630
+ " ",
631
+ "인"
632
+ ],
633
+ [
634
+ " ",
635
+ "있"
636
+ ],
637
+ [
638
+ " ",
639
+ "in"
640
+ ],
641
+ [
642
+ " ",
643
+ "re"
644
+ ],
645
+ [
646
+ "a",
647
+ "l"
648
+ ],
649
+ [
650
+ "a",
651
+ "r"
652
+ ],
653
+ [
654
+ "a",
655
+ "tion"
656
+ ],
657
+ [
658
+ "c",
659
+ "e"
660
+ ],
661
+ [
662
+ "c",
663
+ "i"
664
+ ],
665
+ [
666
+ "e",
667
+ "e"
668
+ ],
669
+ [
670
+ "e",
671
+ "l"
672
+ ],
673
+ [
674
+ "e",
675
+ "n"
676
+ ],
677
+ [
678
+ "e",
679
+ "ar"
680
+ ],
681
+ [
682
+ "f",
683
+ "i"
684
+ ],
685
+ [
686
+ "g",
687
+ "en"
688
+ ],
689
+ [
690
+ "i",
691
+ "z"
692
+ ],
693
+ [
694
+ "i",
695
+ "gen"
696
+ ],
697
+ [
698
+ "l",
699
+ "u"
700
+ ],
701
+ [
702
+ "l",
703
+ "igen"
704
+ ],
705
+ [
706
+ "m",
707
+ "p"
708
+ ],
709
+ [
710
+ "n",
711
+ "d"
712
+ ],
713
+ [
714
+ "n",
715
+ "ing"
716
+ ],
717
+ [
718
+ "o",
719
+ "lu"
720
+ ],
721
+ [
722
+ "o",
723
+ "mp"
724
+ ],
725
+ [
726
+ "r",
727
+ "ti"
728
+ ],
729
+ [
730
+ "t",
731
+ "ation"
732
+ ],
733
+ [
734
+ "t",
735
+ "el"
736
+ ],
737
+ [
738
+ "u",
739
+ "tation"
740
+ ],
741
+ [
742
+ "v",
743
+ "olu"
744
+ ],
745
+ [
746
+ "、",
747
+ "自"
748
+ ],
749
+ [
750
+ "あ",
751
+ "り"
752
+ ],
753
+ [
754
+ "い",
755
+ "ま"
756
+ ],
757
+ [
758
+ "が",
759
+ "急"
760
+ ],
761
+ [
762
+ "し",
763
+ "て"
764
+ ],
765
+ [
766
+ "す",
767
+ "。"
768
+ ],
769
+ [
770
+ "で",
771
+ "あり"
772
+ ],
773
+ [
774
+ "に",
775
+ "進"
776
+ ],
777
+ [
778
+ "の",
779
+ "首"
780
+ ],
781
+ [
782
+ "は",
783
+ "東"
784
+ ],
785
+ [
786
+ "世",
787
+ "界"
788
+ ],
789
+ [
790
+ "习",
791
+ "模"
792
+ ],
793
+ [
794
+ "京",
795
+ "であり"
796
+ ],
797
+ [
798
+ "処",
799
+ "理"
800
+ ],
801
+ [
802
+ "变",
803
+ "世界"
804
+ ],
805
+ [
806
+ "和",
807
+ "深"
808
+ ],
809
+ [
810
+ "在",
811
+ "改"
812
+ ],
813
+ [
814
+ "型",
815
+ "正"
816
+ ],
817
+ [
818
+ "学",
819
+ "习模"
820
+ ],
821
+ [
822
+ "局",
823
+ "。"
824
+ ],
825
+ [
826
+ "展",
827
+ "して"
828
+ ],
829
+ [
830
+ "工",
831
+ "智"
832
+ ],
833
+ [
834
+ "度",
835
+ "学习模"
836
+ ],
837
+ [
838
+ "技",
839
+ "术"
840
+ ],
841
+ [
842
+ "本",
843
+ "の首"
844
+ ],
845
+ [
846
+ "格",
847
+ "局。"
848
+ ],
849
+ [
850
+ "然",
851
+ "言"
852
+ ],
853
+ [
854
+ "的",
855
+ "技术"
856
+ ],
857
+ [
858
+ "能",
859
+ "和深"
860
+ ],
861
+ [
862
+ "語",
863
+ "処理"
864
+ ],
865
+ [
866
+ "速",
867
+ "に進"
868
+ ],
869
+ [
870
+ "都",
871
+ "は東"
872
+ ],
873
+ [
874
+ "공",
875
+ "지"
876
+ ],
877
+ [
878
+ "국",
879
+ "의"
880
+ ],
881
+ [
882
+ "니",
883
+ "다"
884
+ ],
885
+ [
886
+ "도",
887
+ "는"
888
+ ],
889
+ [
890
+ "르",
891
+ "게"
892
+ ],
893
+ [
894
+ "민",
895
+ "국의"
896
+ ],
897
+ [
898
+ "술",
899
+ "이"
900
+ ],
901
+ [
902
+ "습",
903
+ "니다"
904
+ ],
905
+ [
906
+ "울",
907
+ "이"
908
+ ],
909
+ [
910
+ "전",
911
+ "하"
912
+ ],
913
+ [
914
+ "한",
915
+ "민국의"
916
+ ],
917
+ [
918
+ " a",
919
+ "re"
920
+ ],
921
+ [
922
+ " a",
923
+ "nd"
924
+ ],
925
+ [
926
+ "tion",
927
+ "iz"
928
+ ],
929
+ [
930
+ " A",
931
+ "rti"
932
+ ],
933
+ [
934
+ " c",
935
+ "omp"
936
+ ],
937
+ [
938
+ " d",
939
+ "ee"
940
+ ],
941
+ [
942
+ " l",
943
+ "ear"
944
+ ],
945
+ [
946
+ " 人",
947
+ "工智"
948
+ ],
949
+ [
950
+ " 日",
951
+ "本の首"
952
+ ],
953
+ [
954
+ " 기",
955
+ "술이"
956
+ ],
957
+ [
958
+ " 대",
959
+ "한민국의"
960
+ ],
961
+ [
962
+ " 발",
963
+ "전하"
964
+ ],
965
+ [
966
+ " 빠",
967
+ "르게"
968
+ ],
969
+ [
970
+ " 서",
971
+ "울이"
972
+ ],
973
+ [
974
+ " 수",
975
+ "도는"
976
+ ],
977
+ [
978
+ " 인",
979
+ "공지"
980
+ ],
981
+ [
982
+ " 있",
983
+ "습니다"
984
+ ],
985
+ [
986
+ " in",
987
+ "tel"
988
+ ],
989
+ [
990
+ " re",
991
+ "volu"
992
+ ],
993
+ [
994
+ "ci",
995
+ "al"
996
+ ],
997
+ [
998
+ "fi",
999
+ "cial"
1000
+ ],
1001
+ [
1002
+ "ligen",
1003
+ "ce"
1004
+ ],
1005
+ [
1006
+ "utation",
1007
+ "."
1008
+ ],
1009
+ [
1010
+ "、自",
1011
+ "然言"
1012
+ ],
1013
+ [
1014
+ "いま",
1015
+ "す。"
1016
+ ],
1017
+ [
1018
+ "が急",
1019
+ "速に進"
1020
+ ],
1021
+ [
1022
+ "京であり",
1023
+ "、自然言"
1024
+ ],
1025
+ [
1026
+ "变世界",
1027
+ "的技术"
1028
+ ],
1029
+ [
1030
+ "在改",
1031
+ "变世界的技术"
1032
+ ],
1033
+ [
1034
+ "型正",
1035
+ "在改变世界的技术"
1036
+ ],
1037
+ [
1038
+ "展して",
1039
+ "います。"
1040
+ ],
1041
+ [
1042
+ "度学习模",
1043
+ "型正在改变世界的技术"
1044
+ ],
1045
+ [
1046
+ "能和深",
1047
+ "度学习模型正在改变世界的技术"
1048
+ ],
1049
+ [
1050
+ "語処理",
1051
+ "が急速に進"
1052
+ ],
1053
+ [
1054
+ "都は東",
1055
+ "京であり、自然言"
1056
+ ],
1057
+ [
1058
+ "tioniz",
1059
+ "ing"
1060
+ ],
1061
+ [
1062
+ " Arti",
1063
+ "ficial"
1064
+ ],
1065
+ [
1066
+ " comp",
1067
+ "utation."
1068
+ ],
1069
+ [
1070
+ " dee",
1071
+ "p"
1072
+ ],
1073
+ [
1074
+ " lear",
1075
+ "ning"
1076
+ ],
1077
+ [
1078
+ " 人工智",
1079
+ "能和深度学习模型正在改变世界的技术"
1080
+ ],
1081
+ [
1082
+ " 日本の首",
1083
+ "都は東京であり、自然言"
1084
+ ],
1085
+ [
1086
+ " 발전하",
1087
+ "고"
1088
+ ],
1089
+ [
1090
+ " 서울이",
1091
+ "며"
1092
+ ],
1093
+ [
1094
+ " 인공지",
1095
+ "능"
1096
+ ],
1097
+ [
1098
+ " 있습니다",
1099
+ "."
1100
+ ],
1101
+ [
1102
+ " intel",
1103
+ "ligence"
1104
+ ],
1105
+ [
1106
+ " revolu",
1107
+ "tionizing"
1108
+ ],
1109
+ [
1110
+ "語処理が急速に進",
1111
+ "展しています。"
1112
+ ],
1113
+ [
1114
+ " 人工智能和深度学习模型正在改变世界的技术",
1115
+ "格局。"
1116
+ ],
1117
+ [
1118
+ " 日本の首都は東京であり、自然言",
1119
+ "語処理が急速に進展しています。"
1120
+ ]
1121
+ ]
1122
+ }
1123
+ }