divilian commited on
Commit
b36d6fa
·
verified ·
1 Parent(s): 2dc4c6f

Upload tokenizer.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer.json +94 -996
tokenizer.json CHANGED
@@ -22,7 +22,7 @@
22
  "special": true
23
  },
24
  {
25
- "id": 2,
26
  "content": "<bos>",
27
  "single_word": false,
28
  "lstrip": false,
@@ -31,7 +31,7 @@
31
  "special": true
32
  },
33
  {
34
- "id": 3,
35
  "content": "<eos>",
36
  "single_word": false,
37
  "lstrip": false,
@@ -95,1004 +95,102 @@
95
  "vocab": {
96
  "<unk>": 0,
97
  "<pad>": 1,
98
- "<bos>": 2,
99
- "<eos>": 3,
100
  ",": 4,
101
- ":": 5,
102
  ".": 6,
103
- "the": 7,
104
  "and": 8,
105
  "to": 9,
106
- "i": 10,
107
- "of": 11,
108
- ";": 12,
109
- "you": 13,
110
- "my": 14,
111
- "a": 15,
112
- "that": 16,
113
- "?": 17,
114
- "in": 18,
115
- "!": 19,
116
- "is": 20,
117
- "not": 21,
118
- "for": 22,
119
- "with": 23,
120
- "me": 24,
121
- "it": 25,
122
- "be": 26,
123
- "your": 27,
124
- "his": 28,
125
- "but": 29,
126
- "this": 30,
127
- "he": 31,
128
- "have": 32,
129
- "as": 33,
130
- "thou": 34,
131
- "him": 35,
132
- "so": 36,
133
- "what": 37,
134
- "thy": 38,
135
- "will": 39,
136
- "no": 40,
137
- "by": 41,
138
- "all": 42,
139
- "king": 43,
140
- "we": 44,
141
- "shall": 45,
142
- "her": 46,
143
- "if": 47,
144
- "our": 48,
145
- "are": 49,
146
- "do": 50,
147
- "thee": 51,
148
- "now": 52,
149
- "lord": 53,
150
- "on": 54,
151
- "good": 55,
152
- "come": 56,
153
- "from": 57,
154
- "sir": 58,
155
- "or": 59,
156
- "which": 60,
157
- "more": 61,
158
- "then": 62,
159
- "at": 63,
160
- "o": 64,
161
- "would": 65,
162
- "was": 66,
163
- "they": 67,
164
- "how": 68,
165
- "here": 69,
166
- "well": 70,
167
- "she": 71,
168
- "than": 72,
169
- "their": 73,
170
- "them": 74,
171
- "duke": 75,
172
- "am": 76,
173
- "hath": 77,
174
- "say": 78,
175
- "let": 79,
176
- "when": 80,
177
- "i'll": 81,
178
- "one": 82,
179
- "go": 83,
180
- "were": 84,
181
- "love": 85,
182
- "may": 86,
183
- "us": 87,
184
- "make": 88,
185
- "upon": 89,
186
- "yet": 90,
187
- "richard": 91,
188
- "like": 92,
189
- "there": 93,
190
- "must": 94,
191
- "should": 95,
192
- "an": 96,
193
- "first": 97,
194
- "queen": 98,
195
- "why": 99,
196
- "had": 100,
197
- "know": 101,
198
- "man": 102,
199
- "did": 103,
200
- "'tis": 104,
201
- "where": 105,
202
- "see": 106,
203
- "some": 107,
204
- "too": 108,
205
- "death": 109,
206
- "give": 110,
207
- "who": 111,
208
- "speak": 112,
209
- "take": 113,
210
- "these": 114,
211
- "edward": 115,
212
- "york": 116,
213
- "mine": 117,
214
- "such": 118,
215
- "up": 119,
216
- "henry": 120,
217
- "out": 121,
218
- "romeo": 122,
219
- "can": 123,
220
- "father": 124,
221
- "tell": 125,
222
- "time": 126,
223
- "gloucester": 127,
224
- "most": 128,
225
- "lady": 129,
226
- "son": 130,
227
- "nor": 131,
228
- "vincentio": 132,
229
- "hear": 133,
230
- "life": 134,
231
- "made": 135,
232
- "'": 136,
233
- "god": 137,
234
- "art": 138,
235
- "much": 139,
236
- "think": 140,
237
- "warwick": 141,
238
- "heart": 142,
239
- "never": 143,
240
- "doth": 144,
241
- "brother": 145,
242
- "before": 146,
243
- "both": 147,
244
- "cannot": 148,
245
- "any": 149,
246
- "petruchio": 150,
247
- "true": 151,
248
- "being": 152,
249
- "thus": 153,
250
- "ay": 154,
251
- "away": 155,
252
- "blood": 156,
253
- "been": 157,
254
- "name": 158,
255
- "fair": 159,
256
- "coriolanus": 160,
257
- "look": 161,
258
- "men": 162,
259
- "noble": 163,
260
- "again": 164,
261
- "menenius": 165,
262
- "very": 166,
263
- "day": 167,
264
- "hand": 168,
265
- "own": 169,
266
- "pray": 170,
267
- "done": 171,
268
- "juliet": 172,
269
- "second": 173,
270
- "sweet": 174,
271
- "myself": 175,
272
- "leave": 176,
273
- "great": 177,
274
- "therefore": 178,
275
- "against": 179,
276
- "though": 180,
277
- "poor": 181,
278
- "honour": 182,
279
- "down": 183,
280
- "hast": 184,
281
- "prince": 185,
282
- "angelo": 186,
283
- "way": 187,
284
- "fear": 188,
285
- "old": 189,
286
- "nay": 190,
287
- "heaven": 191,
288
- "call": 192,
289
- "till": 193,
290
- "eyes": 194,
291
- "clarence": 195,
292
- "live": 196,
293
- "world": 197,
294
- "nurse": 198,
295
- "stay": 199,
296
- "comes": 200,
297
- "grace": 201,
298
- "many": 202,
299
- "even": 203,
300
- "stand": 204,
301
- "die": 205,
302
- "ever": 206,
303
- "iii": 207,
304
- "nothing": 208,
305
- "wife": 209,
306
- "bear": 210,
307
- "dead": 211,
308
- "whose": 212,
309
- "night": 213,
310
- "--": 214,
311
- "other": 215,
312
- "bolingbroke": 216,
313
- "isabella": 217,
314
- "friends": 218,
315
- "friar": 219,
316
- "leontes": 220,
317
- "head": 221,
318
- "buckingham": 222,
319
- "peace": 223,
320
- "unto": 224,
321
- "those": 225,
322
- "better": 226,
323
- "gone": 227,
324
- "word": 228,
325
- "mother": 229,
326
- "off": 230,
327
- "tranio": 231,
328
- "hence": 232,
329
- "house": 233,
330
- "two": 234,
331
- "could": 235,
332
- "lucio": 236,
333
- "news": 237,
334
- "since": 238,
335
- "still": 239,
336
- "marcius": 240,
337
- "master": 241,
338
- "gentleman": 242,
339
- "little": 243,
340
- "sicinius": 244,
341
- "daughter": 245,
342
- "lords": 246,
343
- "thing": 247,
344
- "soul": 248,
345
- "put": 249,
346
- "once": 250,
347
- "whom": 251,
348
- "himself": 252,
349
- "camillo": 253,
350
- "face": 254,
351
- "margaret": 255,
352
- "o'": 256,
353
- "set": 257,
354
- "capulet": 258,
355
- "else": 259,
356
- "ere": 260,
357
- "iv": 261,
358
- "long": 262,
359
- "thine": 263,
360
- "elizabeth": 264,
361
- "words": 265,
362
- "katharina": 266,
363
- "none": 267,
364
- "might": 268,
365
- "rest": 269,
366
- "best": 270,
367
- "crown": 271,
368
- "power": 272,
369
- "young": 273,
370
- "madam": 274,
371
- "tongue": 275,
372
- "citizen": 276,
373
- "dear": 277,
374
- "part": 278,
375
- "bring": 279,
376
- "gentle": 280,
377
- "vi": 281,
378
- "farewell": 282,
379
- "ii": 283,
380
- "keep": 284,
381
- "hope": 285,
382
- "right": 286,
383
- "every": 287,
384
- "find": 288,
385
- "lucentio": 289,
386
- "pardon": 290,
387
- "said": 291,
388
- "bid": 292,
389
- "came": 293,
390
- "forth": 294,
391
- "hastings": 295,
392
- "hortensio": 296,
393
- "earth": 297,
394
- "hands": 298,
395
- "home": 299,
396
- "into": 300,
397
- "back": 301,
398
- "brutus": 302,
399
- "cause": 303,
400
- "welcome": 304,
401
- "about": 305,
402
- "baptista": 306,
403
- "boy": 307,
404
- "dost": 308,
405
- "hold": 309,
406
- "tears": 310,
407
- "please": 311,
408
- "rome": 312,
409
- "i'": 313,
410
- "provost": 314,
411
- "that's": 315,
412
- "help": 316,
413
- "people": 317,
414
- "full": 318,
415
- "heard": 319,
416
- "makes": 320,
417
- "thought": 321,
418
- "after": 322,
419
- "cousin": 323,
420
- "indeed": 324,
421
- "show": 325,
422
- "escalus": 326,
423
- "grumio": 327,
424
- "husband": 328,
425
- "let's": 329,
426
- "mind": 330,
427
- "place": 331,
428
- "cominius": 332,
429
- "marry": 333,
430
- "pompey": 334,
431
- "wilt": 335,
432
- "friend": 336,
433
- "has": 337,
434
- "mistress": 338,
435
- "what's": 339,
436
- "mean": 340,
437
- "shame": 341,
438
- "state": 342,
439
- "gremio": 343,
440
- "within": 344,
441
- "clifford": 345,
442
- "servant": 346,
443
- "while": 347,
444
- "he's": 348,
445
- "hither": 349,
446
- "aufidius": 350,
447
- "gracious": 351,
448
- "last": 352,
449
- "only": 353,
450
- "answer": 354,
451
- "duchess": 355,
452
- "northumberland": 356,
453
- "rather": 357,
454
- "royal": 358,
455
- "eye": 359,
456
- "far": 360,
457
- "lie": 361,
458
- "mercutio": 362,
459
- "prove": 363,
460
- "thousand": 364,
461
- "another": 365,
462
- "paulina": 366,
463
- "third": 367,
464
- "claudio": 368,
465
- "meet": 369,
466
- "murderer": 370,
467
- "child": 371,
468
- "shalt": 372,
469
- "comfort": 373,
470
- "joy": 374,
471
- "lay": 375,
472
- "lies": 376,
473
- "sorrow": 377,
474
- "use": 378,
475
- "we'll": 379,
476
- "benvolio": 380,
477
- "beseech": 381,
478
- "grief": 382,
479
- "polixenes": 383,
480
- "autolycus": 384,
481
- "less": 385,
482
- "sun": 386,
483
- "war": 387,
484
- "end": 388,
485
- "father's": 389,
486
- "fellow": 390,
487
- "fortune": 391,
488
- "happy": 392,
489
- "hour": 393,
490
- "enough": 394,
491
- "holy": 395,
492
- "matter": 396,
493
- "montague": 397,
494
- "thank": 398,
495
- "arms": 399,
496
- "business": 400,
497
- "grave": 401,
498
- "hate": 402,
499
- "things": 403,
500
- "years": 404,
501
- "bed": 405,
502
- "clown": 406,
503
- "lives": 407,
504
- "prospero": 408,
505
- "truth": 409,
506
- "body": 410,
507
- "faith": 411,
508
- "fall": 412,
509
- "light": 413,
510
- "pity": 414,
511
- "three": 415,
512
- "without": 416,
513
- "get": 417,
514
- "kind": 418,
515
- "nature": 419,
516
- "save": 420,
517
- "to-morrow": 421,
518
- "kate": 422,
519
- "send": 423,
520
- "swear": 424,
521
- "there's": 425,
522
- "turn": 426,
523
- "ah": 427,
524
- "believe": 428,
525
- "bianca": 429,
526
- "false": 430,
527
- "fight": 431,
528
- "gods": 432,
529
- "saw": 433,
530
- "tybalt": 434,
531
- "follow": 435,
532
- "law": 436,
533
- "does": 437,
534
- "looks": 438,
535
- "means": 439,
536
- "present": 440,
537
- "villain": 441,
538
- "yours": 442,
539
- "yourself": 443,
540
- "anne": 444,
541
- "aumerle": 445,
542
- "bloody": 446,
543
- "foul": 447,
544
- "left": 448,
545
- "ne'er": 449,
546
- "sleep": 450,
547
- "talk": 451,
548
- "volumnia": 452,
549
- "city": 453,
550
- "laurence": 454,
551
- "uncle": 455,
552
- "land": 456,
553
- "mercy": 457,
554
- "need": 458,
555
- "servingman": 459,
556
- "told": 460,
557
- "woman": 461,
558
- "worthy": 462,
559
- "messenger": 463,
560
- "proud": 464,
561
- "sea": 465,
562
- "shepherd": 466,
563
- "sit": 467,
564
- "wish": 468,
565
- "because": 469,
566
- "breath": 470,
567
- "gaunt": 471,
568
- "high": 472,
569
- "justice": 473,
570
- "play": 474,
571
- "sword": 475,
572
- "together": 476,
573
- "biondello": 477,
574
- "doubt": 478,
575
- "either": 479,
576
- "fire": 480,
577
- "horse": 481,
578
- "john": 482,
579
- "majesty": 483,
580
- "sister": 484,
581
- "through": 485,
582
- "thyself": 486,
583
- "'twas": 487,
584
- "break": 488,
585
- "children": 489,
586
- "seen": 490,
587
- "sound": 491,
588
- "sovereign": 492,
589
- "under": 493,
590
- "woe": 494,
591
- "catesby": 495,
592
- "days": 496,
593
- "heavy": 497,
594
- "here's": 498,
595
- "maid": 499,
596
- "care": 500,
597
- "gentlemen": 501,
598
- "age": 502,
599
- "canst": 503,
600
- "content": 504,
601
- "ears": 505,
602
- "edward's": 506,
603
- "florizel": 507,
604
- "fly": 508,
605
- "haste": 509,
606
- "kill": 510,
607
- "norfolk": 511,
608
- "paris": 512,
609
- "purpose": 513,
610
- "ready": 514,
611
- "says": 515,
612
- "signior": 516,
613
- "times": 517,
614
- "traitor": 518,
615
- "wrong": 519,
616
- "alone": 520,
617
- "each": 521,
618
- "grey": 522,
619
- "hermione": 523,
620
- "late": 524,
621
- "liege": 525,
622
- "lost": 526,
623
- "new": 527,
624
- "oath": 528,
625
- "reason": 529,
626
- "strange": 530,
627
- "warrant": 531,
628
- "weep": 532,
629
- "alas": 533,
630
- "brought": 534,
631
- "cry": 535,
632
- "kiss": 536,
633
- "mark": 537,
634
- "rivers": 538,
635
- "slain": 539,
636
- "didst": 540,
637
- "france": 541,
638
- "free": 542,
639
- "ground": 543,
640
- "having": 544,
641
- "knows": 545,
642
- "lest": 546,
643
- "loss": 547,
644
- "married": 548,
645
- "seem": 549,
646
- "sent": 550,
647
- "spirit": 551,
648
- "stands": 552,
649
- "straight": 553,
650
- "strike": 554,
651
- "thoughts": 555,
652
- "born": 556,
653
- "cold": 557,
654
- "found": 558,
655
- "near": 559,
656
- "person": 560,
657
- "remember": 561,
658
- "report": 562,
659
- "return": 563,
660
- "sebastian": 564,
661
- "service": 565,
662
- "thanks": 566,
663
- "ye": 567,
664
- "charge": 568,
665
- "common": 569,
666
- "desire": 570,
667
- "hours": 571,
668
- "lose": 572,
669
- "richmond": 573,
670
- "senator": 574,
671
- "sight": 575,
672
- "sin": 576,
673
- "'twere": 577,
674
- "air": 578,
675
- "fie": 579,
676
- "fool": 580,
677
- "foot": 581,
678
- "general": 582,
679
- "god's": 583,
680
- "itself": 584,
681
- "soon": 585,
682
- "sure": 586,
683
- "tender": 587,
684
- "widow": 588,
685
- "yield": 589,
686
- "arm": 590,
687
- "deep": 591,
688
- "duty": 592,
689
- "enemy": 593,
690
- "fault": 594,
691
- "prison": 595,
692
- "prithee": 596,
693
- "women": 597,
694
- "yea": 598,
695
- "you'll": 599,
696
- "command": 600,
697
- "deed": 601,
698
- "honest": 602,
699
- "known": 603,
700
- "mad": 604,
701
- "past": 605,
702
- "patience": 606,
703
- "saint": 607,
704
- "she's": 608,
705
- "trust": 609,
706
- "twenty": 610,
707
- "unless": 611,
708
- "antonio": 612,
709
- "bound": 613,
710
- "citizens": 614,
711
- "cut": 615,
712
- "dare": 616,
713
- "fearful": 617,
714
- "heavens": 618,
715
- "heir": 619,
716
- "ill": 620,
717
- "lewis": 621,
718
- "o'er": 622,
719
- "oxford": 623,
720
- "something": 624,
721
- "ten": 625,
722
- "yes": 626,
723
- "beat": 627,
724
- "beauty": 628,
725
- "company": 629,
726
- "draw": 630,
727
- "ear": 631,
728
- "gonzalo": 632,
729
- "half": 633,
730
- "hearts": 634,
731
- "open": 635,
732
- "revenge": 636,
733
- "serve": 637,
734
- "voices": 638,
735
- "wear": 639,
736
- "withal": 640,
737
- "brave": 641,
738
- "hark": 642,
739
- "is't": 643,
740
- "marriage": 644,
741
- "neither": 645,
742
- "point": 646,
743
- "read": 647,
744
- "side": 648,
745
- "sirrah": 649,
746
- "tale": 650,
747
- "virtue": 651,
748
- "worse": 652,
749
- "ask": 653,
750
- "become": 654,
751
- "change": 655,
752
- "counsel": 656,
753
- "country": 657,
754
- "field": 658,
755
- "hell": 659,
756
- "king's": 660,
757
- "knew": 661,
758
- "lancaster": 662,
759
- "loving": 663,
760
- "methinks": 664,
761
- "next": 665,
762
- "pleasure": 666,
763
- "sake": 667,
764
- "seek": 668,
765
- "work": 669,
766
- "youth": 670,
767
- "behold": 671,
768
- "brother's": 672,
769
- "coming": 673,
770
- "course": 674,
771
- "court": 675,
772
- "enemies": 676,
773
- "fast": 677,
774
- "further": 678,
775
- "gates": 679,
776
- "given": 680,
777
- "met": 681,
778
- "miranda": 682,
779
- "pale": 683,
780
- "tower": 684,
781
- "confess": 685,
782
- "elbow": 686,
783
- "gave": 687,
784
- "ha": 688,
785
- "ho": 689,
786
- "merry": 690,
787
- "rich": 691,
788
- "run": 692,
789
- "souls": 693,
790
- "strength": 694,
791
- "themselves": 695,
792
- "to-day": 696,
793
- "took": 697,
794
- "along": 698,
795
- "banish'd": 699,
796
- "between": 700,
797
- "curse": 701,
798
- "just": 702,
799
- "lips": 703,
800
- "pass": 704,
801
- "peter": 705,
802
- "sad": 706,
803
- "same": 707,
804
- "sworn": 708,
805
- "title": 709,
806
- "already": 710,
807
- "bad": 711,
808
- "bold": 712,
809
- "bosom": 713,
810
- "dream": 714,
811
- "england": 715,
812
- "george": 716,
813
- "goes": 717,
814
- "issue": 718,
815
- "loved": 719,
816
- "office": 720,
817
- "perdita": 721,
818
- "pluck": 722,
819
- "post": 723,
820
- "sons": 724,
821
- "spoke": 725,
822
- "thomas": 726,
823
- "whilst": 727,
824
- "wind": 728,
825
- "fetch": 729,
826
- "hadst": 730,
827
- "jest": 731,
828
- "learn": 732,
829
- "loves": 733,
830
- "officer": 734,
831
- "over": 735,
832
- "soldiers": 736,
833
- "stanley": 737,
834
- "subject": 738,
835
- "tribunes": 739,
836
- "dangerous": 740,
837
- "entreat": 741,
838
- "fit": 742,
839
- "foe": 743,
840
- "forget": 744,
841
- "grant": 745,
842
- "green": 746,
843
- "often": 747,
844
- "presence": 748,
845
- "sly": 749,
846
- "soldier": 750,
847
- "speed": 751,
848
- "suit": 752,
849
- "thence": 753,
850
- "to-night": 754,
851
- "voice": 755,
852
- "wounds": 756,
853
- "attend": 757,
854
- "black": 758,
855
- "gold": 759,
856
- "mariana": 760,
857
- "mighty": 761,
858
- "order": 762,
859
- "quarrel": 763,
860
- "rage": 764,
861
- "request": 765,
862
- "seems": 766,
863
- "soft": 767,
864
- "strong": 768,
865
- "throne": 769,
866
- "wars": 770,
867
- "wert": 771,
868
- "wit": 772,
869
- "worth": 773,
870
- "appear": 774,
871
- "battle": 775,
872
- "begin": 776,
873
- "brief": 777,
874
- "buy": 778,
875
- "call'd": 779,
876
- "case": 780,
877
- "consent": 781,
878
- "deeds": 782,
879
- "deny": 783,
880
- "highness": 784,
881
- "kings": 785,
882
- "lartius": 786,
883
- "london": 787,
884
- "look'd": 788,
885
- "march": 789,
886
- "morning": 790,
887
- "princely": 791,
888
- "somerset": 792,
889
- "throw": 793,
890
- "want": 794,
891
- "wherein": 795,
892
- "win": 796,
893
- "above": 797,
894
- "almost": 798,
895
- "ancient": 799,
896
- "breast": 800,
897
- "consul": 801,
898
- "devil": 802,
899
- "earl": 803,
900
- "faults": 804,
901
- "feel": 805,
902
- "got": 806,
903
- "harm": 807,
904
- "heads": 808,
905
- "hot": 809,
906
- "kill'd": 810,
907
- "man's": 811,
908
- "move": 812,
909
- "prayers": 813,
910
- "presently": 814,
911
- "pretty": 815,
912
- "ratcliff": 816,
913
- "speech": 817,
914
- "thither": 818,
915
- "valiant": 819,
916
- "watch": 820,
917
- "water": 821,
918
- "whence": 822,
919
- "wise": 823,
920
- "wonder": 824,
921
- "3": 825,
922
- "alack": 826,
923
- "e'er": 827,
924
- "five": 828,
925
- "forward": 829,
926
- "hang": 830,
927
- "knock": 831,
928
- "least": 832,
929
- "mayor": 833,
930
- "measure": 834,
931
- "mowbray": 835,
932
- "murder": 836,
933
- "poison": 837,
934
- "roman": 838,
935
- "slave": 839,
936
- "to't": 840,
937
- "towards": 841,
938
- "whether": 842,
939
- "'em": 843,
940
- "'t": 844,
941
- "anon": 845,
942
- "ariel": 846,
943
- "awhile": 847,
944
- "close": 848,
945
- "curtis": 849,
946
- "flesh": 850,
947
- "hearing": 851,
948
- "hereford": 852,
949
- "keeper": 853,
950
- "living": 854,
951
- "moon": 855,
952
- "mortal": 856,
953
- "music": 857,
954
- "promise": 858,
955
- "touch": 859,
956
- "virgilia": 860,
957
- "virtuous": 861,
958
- "witness": 862,
959
- "wouldst": 863,
960
- "antigonus": 864,
961
- "base": 865,
962
- "besides": 866,
963
- "blows": 867,
964
- "breathe": 868,
965
- "chance": 869,
966
- "deserved": 870,
967
- "do't": 871,
968
- "goodly": 872,
969
- "greater": 873,
970
- "grow": 874,
971
- "guilty": 875,
972
- "lawful": 876,
973
- "ourselves": 877,
974
- "patient": 878,
975
- "pay": 879,
976
- "quickly": 880,
977
- "toward": 881,
978
- "wast": 882,
979
- "weeping": 883,
980
- "wherefore": 884,
981
- "worst": 885,
982
- "angry": 886,
983
- "beg": 887,
984
- "derby": 888,
985
- "england's": 889,
986
- "exeter": 890,
987
- "feast": 891,
988
- "fled": 892,
989
- "golden": 893,
990
- "henry's": 894,
991
- "laid": 895,
992
- "letters": 896,
993
- "longer": 897,
994
- "mouth": 898,
995
- "needs": 899,
996
- "note": 900,
997
- "offence": 901,
998
- "on't": 902,
999
- "pedant": 903,
1000
- "shows": 904,
1001
- "stir": 905,
1002
- "truly": 906,
1003
- "whither": 907,
1004
- "worship": 908,
1005
- "action": 909,
1006
- "amen": 910,
1007
- "aside": 911,
1008
- "banishment": 912,
1009
- "behind": 913,
1010
- "bohemia": 914,
1011
- "book": 915,
1012
- "choose": 916,
1013
- "clouds": 917,
1014
- "defend": 918,
1015
- "doing": 919,
1016
- "enter": 920,
1017
- "hard": 921,
1018
- "he'll": 922,
1019
- "held": 923,
1020
- "in't": 924,
1021
- "isabel": 925,
1022
- "knee": 926,
1023
- "ladies": 927,
1024
- "liberty": 928,
1025
- "padua": 929,
1026
- "plain": 930,
1027
- "rough": 931,
1028
- "sense": 932,
1029
- "shed": 933,
1030
- "short": 934,
1031
- "slew": 935,
1032
- "small": 936,
1033
- "speaks": 937,
1034
- "subjects": 938,
1035
- "sudden": 939,
1036
- "ta'en": 940,
1037
- "tear": 941,
1038
- "town": 942,
1039
- "until": 943,
1040
- "won": 944,
1041
- "year": 945,
1042
- "act": 946,
1043
- "bawd": 947,
1044
- "bears": 948,
1045
- "blow": 949,
1046
- "bones": 950,
1047
- "bride": 951,
1048
- "broke": 952,
1049
- "certain": 953,
1050
- "conscience": 954,
1051
- "deliver": 955,
1052
- "dry": 956,
1053
- "forgot": 957,
1054
- "hide": 958,
1055
- "hundred": 959,
1056
- "kingdom": 960,
1057
- "lead": 961,
1058
- "leisure": 962,
1059
- "letter": 963,
1060
- "lived": 964,
1061
- "masters": 965,
1062
- "neck": 966,
1063
- "noise": 967,
1064
- "oft": 968,
1065
- "piece": 969,
1066
- "plantagenet": 970,
1067
- "prisoner": 971,
1068
- "stood": 972,
1069
- "victory": 973,
1070
- "visit": 974,
1071
- "'twixt": 975,
1072
- "adieu": 976,
1073
- "alive": 977,
1074
- "barnardine": 978,
1075
- "bitter": 979,
1076
- "blessed": 980,
1077
- "bushy": 981,
1078
- "chamber": 982,
1079
- "commend": 983,
1080
- "country's": 984,
1081
- "danger": 985,
1082
- "drink": 986,
1083
- "few": 987,
1084
- "fine": 988,
1085
- "forbid": 989,
1086
- "four": 990,
1087
- "glad": 991,
1088
- "glory": 992,
1089
- "herself": 993,
1090
- "kept": 994,
1091
- "knees": 995,
1092
- "knowledge": 996,
1093
- "lands": 997,
1094
- "morrow": 998,
1095
- "pride": 999
1096
  },
1097
  "unk_token": "<unk>"
1098
  }
 
22
  "special": true
23
  },
24
  {
25
+ "id": 29,
26
  "content": "<bos>",
27
  "single_word": false,
28
  "lstrip": false,
 
31
  "special": true
32
  },
33
  {
34
+ "id": 30,
35
  "content": "<eos>",
36
  "single_word": false,
37
  "lstrip": false,
 
95
  "vocab": {
96
  "<unk>": 0,
97
  "<pad>": 1,
 
 
98
  ",": 4,
99
+ "the": 5,
100
  ".": 6,
101
+ "of": 7,
102
  "and": 8,
103
  "to": 9,
104
+ "a": 10,
105
+ "in": 11,
106
+ "\"": 12,
107
+ "that": 13,
108
+ "was": 14,
109
+ "is": 15,
110
+ "for": 16,
111
+ "on": 17,
112
+ "with": 18,
113
+ "as": 19,
114
+ "it": 20,
115
+ "he": 21,
116
+ "his": 22,
117
+ "at": 23,
118
+ "by": 24,
119
+ "i": 25,
120
+ ";": 26,
121
+ "be": 27,
122
+ "from": 28,
123
+ "<bos>": 29,
124
+ "<eos>": 30,
125
+ "not": 31,
126
+ ")": 32,
127
+ "but": 33,
128
+ "(": 34,
129
+ "this": 35,
130
+ "had": 36,
131
+ "which": 37,
132
+ "have": 38,
133
+ "are": 39,
134
+ ":": 40,
135
+ "they": 41,
136
+ "an": 42,
137
+ "or": 43,
138
+ "were": 44,
139
+ "her": 45,
140
+ "said": 46,
141
+ "their": 47,
142
+ "has": 48,
143
+ "we": 49,
144
+ "all": 50,
145
+ "who": 51,
146
+ "one": 52,
147
+ "she": 53,
148
+ "you": 54,
149
+ "": 55,
150
+ "": 56,
151
+ "been": 57,
152
+ "will": 58,
153
+ "more": 59,
154
+ "him": 60,
155
+ "when": 61,
156
+ "so": 62,
157
+ "its": 63,
158
+ "would": 64,
159
+ "there": 65,
160
+ "no": 66,
161
+ "after": 67,
162
+ "my": 68,
163
+ "if": 69,
164
+ "out": 70,
165
+ "also": 71,
166
+ "about": 72,
167
+ "them": 73,
168
+ "up": 74,
169
+ "into": 75,
170
+ "two": 76,
171
+ "what": 77,
172
+ "new": 78,
173
+ "first": 79,
174
+ "some": 80,
175
+ "can": 81,
176
+ "time": 82,
177
+ "than": 83,
178
+ "other": 84,
179
+ "our": 85,
180
+ "me": 86,
181
+ "only": 87,
182
+ "over": 88,
183
+ "could": 89,
184
+ "may": 90,
185
+ "?": 91,
186
+ "any": 92,
187
+ "/": 93,
188
+ "then": 94,
189
+ "people": 95,
190
+ "like": 96,
191
+ "now": 97,
192
+ "such": 98,
193
+ "do": 99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194
  },
195
  "unk_token": "<unk>"
196
  }