Update tiny models for Owlv2ForObjectDetection

#2
Files changed (4) hide show
  1. config.json +2 -0
  2. model.safetensors +1 -1
  3. tokenizer.json +125 -125
  4. vocab.json +125 -125
config.json CHANGED
@@ -11,7 +11,9 @@
11
  "projection_dim": 64,
12
  "text_config": {
13
  "attention_dropout": 0.1,
 
14
  "dropout": 0.1,
 
15
  "hidden_size": 64,
16
  "intermediate_size": 37,
17
  "model_type": "owlv2_text_model",
 
11
  "projection_dim": 64,
12
  "text_config": {
13
  "attention_dropout": 0.1,
14
+ "bos_token_id": 1,
15
  "dropout": 0.1,
16
+ "eos_token_id": 2,
17
  "hidden_size": 64,
18
  "intermediate_size": 37,
19
  "model_type": "owlv2_text_model",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e69e2bdf27b5fe17d6a32a53dd4a1c34098c8e643db8308a57c9382d829aa7f5
3
  size 1480104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6e0d2bcd52f3751694036ed585f05097ef5cb2d625c86d121fd12ec9016047
3
  size 1480104
tokenizer.json CHANGED
@@ -263,137 +263,137 @@
263
  "Ł": 164,
264
  "ł": 165,
265
  "Ń": 166,
266
- "e</w>": 167,
267
- "s</w>": 168,
268
- "f</w>": 169,
269
- "d</w>": 170,
270
- "r</w>": 171,
271
- "n</w>": 172,
272
- "l</w>": 173,
273
- "y</w>": 174,
274
- "a</w>": 175,
275
- "c</w>": 176,
276
- "i</w>": 177,
277
- "k</w>": 178,
278
- "g</w>": 179,
279
- "t</w>": 180,
280
- "m</w>": 181,
281
- "p</w>": 182,
282
- "h</w>": 183,
283
  "x</w>": 184,
284
- "ĵ</w>": 185,
285
- "Ľ</w>": 186,
286
- "u</w>": 187,
287
  "o</w>": 188,
288
- "¡</w>": 189,
289
- "v</w>": 190,
290
- "b</w>": 191,
291
- "z</w>": 192,
292
- "w</w>": 193,
293
- "¸</w>": 194,
294
- "ĩ</w>": 195,
295
- "ĸ</w>": 196,
296
- "Ħ</w>": 197,
297
- "Ĭ</w>": 198,
298
- "ĺ</w>": 199,
299
  "©</w>": 200,
300
- "į</w>": 201,
301
- "Ĩ</w>": 202,
302
- "¥</w>": 203,
303
- ":</w>": 204,
304
- "Ŀ</w>": 205,
305
- "ŀ</w>": 206,
306
- "§</w>": 207,
307
- "j</w>": 208,
308
- "¼</w>": 209,
309
- "£</w>": 210,
310
- "¹</w>": 211,
311
- "*</w>": 212,
312
- "µ</w>": 213,
313
- "ģ</w>": 214,
314
- "¢</w>": 215,
315
- "ķ</w>": 216,
316
- "q</w>": 217,
317
- "³</w>": 218,
318
- "ij</w>": 219,
319
- "«</w>": 220,
320
- "ħ</w>": 221,
321
- "ī</w>": 222,
322
- "Ķ</w>": 223,
323
- "¤</w>": 224,
324
- "²</w>": 225,
325
- "Ļ</w>": 226,
326
- "Ĵ</w>": 227,
327
- "#</w>": 228,
328
- "Į</w>": 229,
329
- "ı</w>": 230,
330
- "Ń</w>": 231,
331
- "-</w>": 232,
332
  "ĥ</w>": 233,
333
- "½</w>": 234,
334
- "Ĥ</w>": 235,
335
- ".</w>": 236,
336
- "¶</w>": 237,
337
- "¨</w>": 238,
338
- "®</w>": 239,
339
- "¦</w>": 240,
340
- "ĭ</w>": 241,
341
- "&</w>": 242,
342
- "Ī</w>": 243,
343
- "Ģ</w>": 244,
344
- "±</w>": 245,
345
- "1</w>": 246,
346
- "ľ</w>": 247,
347
- "¯</w>": 248,
348
- "¿</w>": 249,
349
- "Ł</w>": 250,
350
- "8</w>": 251,
351
- "ł</w>": 252,
352
- "5</w>": 253,
353
- "º</w>": 254,
354
- "IJ</w>": 255,
355
- "°</w>": 256,
356
- "»</w>": 257,
357
- "ª</w>": 258,
358
- "¾</w>": 259,
359
- "|</w>": 260,
360
- "·</w>": 261,
361
- "<</w>": 262,
362
- "Ĺ</w>": 263,
363
- "%</w>": 264,
364
- "`</w>": 265,
365
- "]</w>": 266,
366
- "´</w>": 267,
367
- "2</w>": 268,
368
- "@</w>": 269,
369
- "[</w>": 270,
370
- "0</w>": 271,
371
- "¬</w>": 272,
372
- "3</w>": 273,
373
- "$</w>": 274,
374
- ";</w>": 275,
375
- "6</w>": 276,
376
- "9</w>": 277,
377
- "^</w>": 278,
378
- "İ</w>": 279,
379
- "~</w>": 280,
380
- "=</w>": 281,
381
- "\"</w>": 282,
382
- "!</w>": 283,
383
- "></w>": 284,
384
  "}</w>": 285,
385
  ",</w>": 286,
386
- "'</w>": 287,
387
- "+</w>": 288,
388
- "(</w>": 289,
389
- "ļ</w>": 290,
390
- "?</w>": 291,
391
- "/</w>": 292,
392
- "_</w>": 293,
393
- "4</w>": 294,
394
- ")</w>": 295,
395
- "\\</w>": 296,
396
- "7</w>": 297,
397
  "th": 298,
398
  "the</w>": 299,
399
  "in": 300,
 
263
  "Ł": 164,
264
  "ł": 165,
265
  "Ń": 166,
266
+ "i</w>": 167,
267
+ "n</w>": 168,
268
+ "y</w>": 169,
269
+ "a</w>": 170,
270
+ "k</w>": 171,
271
+ "d</w>": 172,
272
+ "u</w>": 173,
273
+ "s</w>": 174,
274
+ "e</w>": 175,
275
+ "h</w>": 176,
276
+ "g</w>": 177,
277
+ "t</w>": 178,
278
+ "r</w>": 179,
279
+ "m</w>": 180,
280
+ "w</w>": 181,
281
+ "~</w>": 182,
282
+ "p</w>": 183,
283
  "x</w>": 184,
284
+ "z</w>": 185,
285
+ "c</w>": 186,
286
+ "l</w>": 187,
287
  "o</w>": 188,
288
+ "b</w>": 189,
289
+ "f</w>": 190,
290
+ "j</w>": 191,
291
+ "¡</w>": 192,
292
+ "Ń</w>": 193,
293
+ "·</w>": 194,
294
+ "Ĭ</w>": 195,
295
+ "v</w>": 196,
296
+ "-</w>": 197,
297
+ "ĵ</w>": 198,
298
+ "Ħ</w>": 199,
299
  "©</w>": 200,
300
+ "ī</w>": 201,
301
+ "Ģ</w>": 202,
302
+ "ĩ</w>": 203,
303
+ "ľ</w>": 204,
304
+ "Ľ</w>": 205,
305
+ "¹</w>": 206,
306
+ "±</w>": 207,
307
+ "¸</w>": 208,
308
+ "ª</w>": 209,
309
+ "Ļ</w>": 210,
310
+ "Ĥ</w>": 211,
311
+ "½</w>": 212,
312
+ "®</w>": 213,
313
+ "Ĵ</w>": 214,
314
+ "ĺ</w>": 215,
315
+ "$</w>": 216,
316
+ ".</w>": 217,
317
+ "¯</w>": 218,
318
+ "¨</w>": 219,
319
+ "'</w>": 220,
320
+ "Ī</w>": 221,
321
+ "³</w>": 222,
322
+ "¿</w>": 223,
323
+ "ħ</w>": 224,
324
+ "°</w>": 225,
325
+ "²</w>": 226,
326
+ "¬</w>": 227,
327
+ "µ</w>": 228,
328
+ "ij</w>": 229,
329
+ "¦</w>": 230,
330
+ "q</w>": 231,
331
+ "ģ</w>": 232,
332
  "ĥ</w>": 233,
333
+ "¢</w>": 234,
334
+ "7</w>": 235,
335
+ "¼</w>": 236,
336
+ "£</w>": 237,
337
+ "&</w>": 238,
338
+ "0</w>": 239,
339
+ "į</w>": 240,
340
+ "ŀ</w>": 241,
341
+ "Ķ</w>": 242,
342
+ "ļ</w>": 243,
343
+ "ı</w>": 244,
344
+ "»</w>": 245,
345
+ "4</w>": 246,
346
+ "«</w>": 247,
347
+ "¤</w>": 248,
348
+ "¾</w>": 249,
349
+ "ĸ</w>": 250,
350
+ "§</w>": 251,
351
+ "Ĩ</w>": 252,
352
+ "´</w>": 253,
353
+ "[</w>": 254,
354
+ "Ĺ</w>": 255,
355
+ "Ł</w>": 256,
356
+ "IJ</w>": 257,
357
+ "Į</w>": 258,
358
+ "Ŀ</w>": 259,
359
+ "¶</w>": 260,
360
+ "ł</w>": 261,
361
+ "+</w>": 262,
362
+ "º</w>": 263,
363
+ "3</w>": 264,
364
+ "¥</w>": 265,
365
+ "`</w>": 266,
366
+ "*</w>": 267,
367
+ "/</w>": 268,
368
+ "!</w>": 269,
369
+ "\"</w>": 270,
370
+ "]</w>": 271,
371
+ "|</w>": 272,
372
+ "^</w>": 273,
373
+ "ĭ</w>": 274,
374
+ "@</w>": 275,
375
+ "5</w>": 276,
376
+ "%</w>": 277,
377
+ "8</w>": 278,
378
+ "?</w>": 279,
379
+ ")</w>": 280,
380
+ ":</w>": 281,
381
+ "ķ</w>": 282,
382
+ "#</w>": 283,
383
+ "<</w>": 284,
384
  "}</w>": 285,
385
  ",</w>": 286,
386
+ "1</w>": 287,
387
+ "_</w>": 288,
388
+ "6</w>": 289,
389
+ "İ</w>": 290,
390
+ "\\</w>": 291,
391
+ "2</w>": 292,
392
+ ";</w>": 293,
393
+ "=</w>": 294,
394
+ "></w>": 295,
395
+ "(</w>": 296,
396
+ "9</w>": 297,
397
  "th": 298,
398
  "the</w>": 299,
399
  "in": 300,
vocab.json CHANGED
@@ -1,91 +1,91 @@
1
  {
2
  "!": 0,
3
- "!</w>": 283,
4
  "\"": 3,
5
- "\"</w>": 282,
6
  "#": 4,
7
- "#</w>": 228,
8
  "$": 5,
9
- "$</w>": 274,
10
  "%": 6,
11
- "%</w>": 264,
12
  "&": 7,
13
- "&</w>": 242,
14
  "'": 8,
15
- "'</w>": 287,
16
  "'s</w>": 363,
17
  "(": 9,
18
- "(</w>": 289,
19
  ")": 10,
20
- ")</w>": 295,
21
  "*": 11,
22
- "*</w>": 212,
23
  "+": 12,
24
- "+</w>": 288,
25
  ",": 13,
26
  ",</w>": 286,
27
  ",@</w>": 622,
28
  "-": 14,
29
- "-</w>": 232,
30
  "-@</w>": 353,
31
  ".": 15,
32
- ".</w>": 236,
33
  ".@</w>": 569,
34
  "/": 16,
35
- "/</w>": 292,
36
  "0": 17,
37
- "0</w>": 271,
38
  "1": 18,
39
- "1</w>": 246,
40
  "2": 19,
41
- "2</w>": 268,
42
  "3": 20,
43
- "3</w>": 273,
44
  "4": 21,
45
- "4</w>": 294,
46
  "5": 22,
47
- "5</w>": 253,
48
  "6": 23,
49
- "6</w>": 276,
50
  "7": 24,
51
- "7</w>": 297,
52
  "8": 25,
53
- "8</w>": 251,
54
  "9": 26,
55
- "9</w>": 277,
56
  ":": 27,
57
- ":</w>": 204,
58
  ";": 28,
59
- ";</w>": 275,
60
  "<": 29,
61
- "<</w>": 262,
62
  "<|endoftext|>": 2,
63
  "<|startoftext|>": 1,
64
  "=": 30,
65
- "=</w>": 281,
66
  ">": 31,
67
- "></w>": 284,
68
  "?": 32,
69
- "?</w>": 291,
70
  "@": 33,
71
  "@,@</w>": 623,
72
  "@-@</w>": 354,
73
  "@.@</w>": 570,
74
- "@</w>": 269,
75
  "[": 34,
76
- "[</w>": 270,
77
  "\\": 35,
78
- "\\</w>": 296,
79
  "]": 36,
80
- "]</w>": 266,
81
  "^": 37,
82
- "^</w>": 278,
83
  "_": 38,
84
- "_</w>": 293,
85
  "`": 39,
86
- "`</w>": 265,
87
  "a": 40,
88
- "a</w>": 175,
89
  "ab": 408,
90
  "able</w>": 675,
91
  "about</w>": 721,
@@ -158,7 +158,7 @@
158
  "au": 448,
159
  "ause</w>": 997,
160
  "b": 41,
161
- "b</w>": 191,
162
  "ba": 687,
163
  "back</w>": 992,
164
  "bar": 821,
@@ -194,7 +194,7 @@
194
  "but</w>": 499,
195
  "by</w>": 369,
196
  "c": 42,
197
- "c</w>": 176,
198
  "ca": 394,
199
  "cal": 820,
200
  "called</w>": 1014,
@@ -243,7 +243,7 @@
243
  "cul": 881,
244
  "cur": 990,
245
  "d": 43,
246
- "d</w>": 170,
247
  "da": 497,
248
  "day</w>": 755,
249
  "de": 352,
@@ -275,7 +275,7 @@
275
  "during</w>": 616,
276
  "dy</w>": 727,
277
  "e": 44,
278
- "e</w>": 167,
279
  "ea": 344,
280
  "eam</w>": 1006,
281
  "ear": 445,
@@ -326,7 +326,7 @@
326
  "ever</w>": 754,
327
  "ex": 417,
328
  "f": 45,
329
- "f</w>": 169,
330
  "fa": 630,
331
  "fac": 893,
332
  "fe": 484,
@@ -355,7 +355,7 @@
355
  "ft</w>": 707,
356
  "fu": 665,
357
  "g": 46,
358
- "g</w>": 179,
359
  "ga": 631,
360
  "game</w>": 697,
361
  "gan</w>": 835,
@@ -378,7 +378,7 @@
378
  "gs</w>": 975,
379
  "gu": 426,
380
  "h": 47,
381
- "h</w>": 183,
382
  "ha": 367,
383
  "had</w>": 459,
384
  "har": 971,
@@ -400,7 +400,7 @@
400
  "however</w>": 867,
401
  "hu": 993,
402
  "i": 48,
403
- "i</w>": 177,
404
  "ic": 409,
405
  "ic</w>": 783,
406
  "ical</w>": 713,
@@ -438,12 +438,12 @@
438
  "its</w>": 480,
439
  "ity</w>": 443,
440
  "j": 49,
441
- "j</w>": 208,
442
  "jo": 585,
443
  "joh": 941,
444
  "ju": 619,
445
  "k": 50,
446
- "k</w>": 178,
447
  "ke": 661,
448
  "ke</w>": 505,
449
  "ked</w>": 653,
@@ -452,7 +452,7 @@
452
  "known</w>": 879,
453
  "ks</w>": 559,
454
  "l": 51,
455
- "l</w>": 173,
456
  "la": 348,
457
  "lan": 606,
458
  "land</w>": 561,
@@ -481,7 +481,7 @@
481
  "lu": 432,
482
  "ly</w>": 342,
483
  "m": 52,
484
- "m</w>": 181,
485
  "ma": 365,
486
  "made</w>": 794,
487
  "man": 444,
@@ -508,7 +508,7 @@
508
  "musi": 808,
509
  "music</w>": 961,
510
  "n": 53,
511
- "n</w>": 172,
512
  "na": 517,
513
  "nam": 810,
514
  "national</w>": 849,
@@ -571,7 +571,7 @@
571
  "ow": 416,
572
  "own</w>": 617,
573
  "p": 55,
574
- "p</w>": 182,
575
  "pa": 593,
576
  "par": 427,
577
  "part</w>": 892,
@@ -604,10 +604,10 @@
604
  "pu": 485,
605
  "publi": 728,
606
  "q": 56,
607
- "q</w>": 217,
608
  "qu": 431,
609
  "r": 57,
610
- "r</w>": 171,
611
  "ra": 355,
612
  "ran": 523,
613
  "re": 304,
@@ -629,7 +629,7 @@
629
  "ru": 419,
630
  "ry</w>": 885,
631
  "s": 58,
632
- "s</w>": 168,
633
  "sa": 510,
634
  "sc": 414,
635
  "sch": 775,
@@ -705,7 +705,7 @@
705
  "sur": 642,
706
  "sy": 673,
707
  "t": 59,
708
- "t</w>": 180,
709
  "ta": 438,
710
  "tain</w>": 1010,
711
  "te": 544,
@@ -775,7 +775,7 @@
775
  "two</w>": 545,
776
  "ty</w>": 584,
777
  "u": 60,
778
- "u</w>": 187,
779
  "ul": 461,
780
  "um": 500,
781
  "um</w>": 743,
@@ -793,7 +793,7 @@
793
  "use</w>": 991,
794
  "used</w>": 701,
795
  "v": 61,
796
- "v</w>": 190,
797
  "ve": 910,
798
  "ve</w>": 371,
799
  "ved</w>": 503,
@@ -809,7 +809,7 @@
809
  "vision</w>": 873,
810
  "vo": 852,
811
  "w": 62,
812
- "w</w>": 193,
813
  "wa": 464,
814
  "war": 768,
815
  "war</w>": 866,
@@ -842,7 +842,7 @@
842
  "x": 63,
843
  "x</w>": 184,
844
  "y": 64,
845
- "y</w>": 174,
846
  "year</w>": 789,
847
  "years</w>": 845,
848
  "ying</w>": 868,
@@ -850,74 +850,74 @@
850
  "yp": 870,
851
  "ys</w>": 711,
852
  "z": 65,
853
- "z</w>": 192,
854
  "zed</w>": 973,
855
  "|": 66,
856
- "|</w>": 260,
857
  "}": 67,
858
  "}</w>": 285,
859
  "~": 68,
860
- "~</w>": 280,
861
  "¡": 69,
862
- "¡</w>": 189,
863
  "¢": 70,
864
- "¢</w>": 215,
865
  "£": 71,
866
- "£</w>": 210,
867
  "¤": 72,
868
- "¤</w>": 224,
869
  "¥": 73,
870
- "¥</w>": 203,
871
  "¦": 74,
872
- "¦</w>": 240,
873
  "§": 75,
874
- "§</w>": 207,
875
  "¨": 76,
876
- "¨</w>": 238,
877
  "©": 77,
878
  "©</w>": 200,
879
  "ª": 78,
880
- "ª</w>": 258,
881
  "«": 79,
882
- "«</w>": 220,
883
  "¬": 80,
884
- "¬</w>": 272,
885
  "®": 81,
886
- "®</w>": 239,
887
  "¯": 82,
888
- "¯</w>": 248,
889
  "°": 83,
890
- "°</w>": 256,
891
  "±": 84,
892
- "±</w>": 245,
893
  "²": 85,
894
- "²</w>": 225,
895
  "³": 86,
896
- "³</w>": 218,
897
  "´": 87,
898
- "´</w>": 267,
899
  "µ": 88,
900
- "µ</w>": 213,
901
  "¶": 89,
902
- "¶</w>": 237,
903
  "·": 90,
904
- "·</w>": 261,
905
  "¸": 91,
906
- "¸</w>": 194,
907
  "¹": 92,
908
- "¹</w>": 211,
909
  "º": 93,
910
- "º</w>": 254,
911
  "»": 94,
912
- "»</w>": 257,
913
  "¼": 95,
914
- "¼</w>": 209,
915
  "½": 96,
916
- "½</w>": 234,
917
  "¾": 97,
918
- "¾</w>": 259,
919
  "¿": 98,
920
- "¿</w>": 249,
921
  "Â": 99,
922
  "Ã": 100,
923
  "Ä": 101,
@@ -956,71 +956,71 @@
956
  "ì": 131,
957
  "ï": 132,
958
  "Ģ": 133,
959
- "Ģ</w>": 244,
960
  "ģ": 134,
961
- "ģ</w>": 214,
962
  "Ĥ": 135,
963
- "Ĥ</w>": 235,
964
  "ĥ": 136,
965
  "ĥ</w>": 233,
966
  "Ħ": 137,
967
- "Ħ</w>": 197,
968
  "ħ": 138,
969
- "ħ</w>": 221,
970
  "Ĩ": 139,
971
- "Ĩ</w>": 202,
972
  "ĩ": 140,
973
- "ĩ</w>": 195,
974
  "Ī": 141,
975
- "Ī</w>": 243,
976
  "ī": 142,
977
- "ī</w>": 222,
978
  "Ĭ": 143,
979
- "Ĭ</w>": 198,
980
  "ĭ": 144,
981
- "ĭ</w>": 241,
982
  "Į": 145,
983
- "Į</w>": 229,
984
  "į": 146,
985
- "į</w>": 201,
986
  "İ": 147,
987
- "İ</w>": 279,
988
  "ı": 148,
989
- "ı</w>": 230,
990
  "IJ": 149,
991
- "IJ</w>": 255,
992
  "ij": 150,
993
- "ij</w>": 219,
994
  "Ĵ": 151,
995
- "Ĵ</w>": 227,
996
  "ĵ": 152,
997
- "ĵ</w>": 185,
998
  "Ķ": 153,
999
- "Ķ</w>": 223,
1000
  "ķ": 154,
1001
- "ķ</w>": 216,
1002
  "ĸ": 155,
1003
- "ĸ</w>": 196,
1004
  "Ĺ": 156,
1005
- "Ĺ</w>": 263,
1006
  "ĺ": 157,
1007
- "ĺ</w>": 199,
1008
  "Ļ": 158,
1009
- "Ļ</w>": 226,
1010
  "ļ": 159,
1011
- "ļ</w>": 290,
1012
  "Ľ": 160,
1013
- "Ľ</w>": 186,
1014
  "ľ": 161,
1015
- "ľ</w>": 247,
1016
  "Ŀ": 162,
1017
- "Ŀ</w>": 205,
1018
  "ŀ": 163,
1019
- "ŀ</w>": 206,
1020
  "Ł": 164,
1021
- "Ł</w>": 250,
1022
  "ł": 165,
1023
- "ł</w>": 252,
1024
  "Ń": 166,
1025
- "Ń</w>": 231
1026
  }
 
1
  {
2
  "!": 0,
3
+ "!</w>": 269,
4
  "\"": 3,
5
+ "\"</w>": 270,
6
  "#": 4,
7
+ "#</w>": 283,
8
  "$": 5,
9
+ "$</w>": 216,
10
  "%": 6,
11
+ "%</w>": 277,
12
  "&": 7,
13
+ "&</w>": 238,
14
  "'": 8,
15
+ "'</w>": 220,
16
  "'s</w>": 363,
17
  "(": 9,
18
+ "(</w>": 296,
19
  ")": 10,
20
+ ")</w>": 280,
21
  "*": 11,
22
+ "*</w>": 267,
23
  "+": 12,
24
+ "+</w>": 262,
25
  ",": 13,
26
  ",</w>": 286,
27
  ",@</w>": 622,
28
  "-": 14,
29
+ "-</w>": 197,
30
  "-@</w>": 353,
31
  ".": 15,
32
+ ".</w>": 217,
33
  ".@</w>": 569,
34
  "/": 16,
35
+ "/</w>": 268,
36
  "0": 17,
37
+ "0</w>": 239,
38
  "1": 18,
39
+ "1</w>": 287,
40
  "2": 19,
41
+ "2</w>": 292,
42
  "3": 20,
43
+ "3</w>": 264,
44
  "4": 21,
45
+ "4</w>": 246,
46
  "5": 22,
47
+ "5</w>": 276,
48
  "6": 23,
49
+ "6</w>": 289,
50
  "7": 24,
51
+ "7</w>": 235,
52
  "8": 25,
53
+ "8</w>": 278,
54
  "9": 26,
55
+ "9</w>": 297,
56
  ":": 27,
57
+ ":</w>": 281,
58
  ";": 28,
59
+ ";</w>": 293,
60
  "<": 29,
61
+ "<</w>": 284,
62
  "<|endoftext|>": 2,
63
  "<|startoftext|>": 1,
64
  "=": 30,
65
+ "=</w>": 294,
66
  ">": 31,
67
+ "></w>": 295,
68
  "?": 32,
69
+ "?</w>": 279,
70
  "@": 33,
71
  "@,@</w>": 623,
72
  "@-@</w>": 354,
73
  "@.@</w>": 570,
74
+ "@</w>": 275,
75
  "[": 34,
76
+ "[</w>": 254,
77
  "\\": 35,
78
+ "\\</w>": 291,
79
  "]": 36,
80
+ "]</w>": 271,
81
  "^": 37,
82
+ "^</w>": 273,
83
  "_": 38,
84
+ "_</w>": 288,
85
  "`": 39,
86
+ "`</w>": 266,
87
  "a": 40,
88
+ "a</w>": 170,
89
  "ab": 408,
90
  "able</w>": 675,
91
  "about</w>": 721,
 
158
  "au": 448,
159
  "ause</w>": 997,
160
  "b": 41,
161
+ "b</w>": 189,
162
  "ba": 687,
163
  "back</w>": 992,
164
  "bar": 821,
 
194
  "but</w>": 499,
195
  "by</w>": 369,
196
  "c": 42,
197
+ "c</w>": 186,
198
  "ca": 394,
199
  "cal": 820,
200
  "called</w>": 1014,
 
243
  "cul": 881,
244
  "cur": 990,
245
  "d": 43,
246
+ "d</w>": 172,
247
  "da": 497,
248
  "day</w>": 755,
249
  "de": 352,
 
275
  "during</w>": 616,
276
  "dy</w>": 727,
277
  "e": 44,
278
+ "e</w>": 175,
279
  "ea": 344,
280
  "eam</w>": 1006,
281
  "ear": 445,
 
326
  "ever</w>": 754,
327
  "ex": 417,
328
  "f": 45,
329
+ "f</w>": 190,
330
  "fa": 630,
331
  "fac": 893,
332
  "fe": 484,
 
355
  "ft</w>": 707,
356
  "fu": 665,
357
  "g": 46,
358
+ "g</w>": 177,
359
  "ga": 631,
360
  "game</w>": 697,
361
  "gan</w>": 835,
 
378
  "gs</w>": 975,
379
  "gu": 426,
380
  "h": 47,
381
+ "h</w>": 176,
382
  "ha": 367,
383
  "had</w>": 459,
384
  "har": 971,
 
400
  "however</w>": 867,
401
  "hu": 993,
402
  "i": 48,
403
+ "i</w>": 167,
404
  "ic": 409,
405
  "ic</w>": 783,
406
  "ical</w>": 713,
 
438
  "its</w>": 480,
439
  "ity</w>": 443,
440
  "j": 49,
441
+ "j</w>": 191,
442
  "jo": 585,
443
  "joh": 941,
444
  "ju": 619,
445
  "k": 50,
446
+ "k</w>": 171,
447
  "ke": 661,
448
  "ke</w>": 505,
449
  "ked</w>": 653,
 
452
  "known</w>": 879,
453
  "ks</w>": 559,
454
  "l": 51,
455
+ "l</w>": 187,
456
  "la": 348,
457
  "lan": 606,
458
  "land</w>": 561,
 
481
  "lu": 432,
482
  "ly</w>": 342,
483
  "m": 52,
484
+ "m</w>": 180,
485
  "ma": 365,
486
  "made</w>": 794,
487
  "man": 444,
 
508
  "musi": 808,
509
  "music</w>": 961,
510
  "n": 53,
511
+ "n</w>": 168,
512
  "na": 517,
513
  "nam": 810,
514
  "national</w>": 849,
 
571
  "ow": 416,
572
  "own</w>": 617,
573
  "p": 55,
574
+ "p</w>": 183,
575
  "pa": 593,
576
  "par": 427,
577
  "part</w>": 892,
 
604
  "pu": 485,
605
  "publi": 728,
606
  "q": 56,
607
+ "q</w>": 231,
608
  "qu": 431,
609
  "r": 57,
610
+ "r</w>": 179,
611
  "ra": 355,
612
  "ran": 523,
613
  "re": 304,
 
629
  "ru": 419,
630
  "ry</w>": 885,
631
  "s": 58,
632
+ "s</w>": 174,
633
  "sa": 510,
634
  "sc": 414,
635
  "sch": 775,
 
705
  "sur": 642,
706
  "sy": 673,
707
  "t": 59,
708
+ "t</w>": 178,
709
  "ta": 438,
710
  "tain</w>": 1010,
711
  "te": 544,
 
775
  "two</w>": 545,
776
  "ty</w>": 584,
777
  "u": 60,
778
+ "u</w>": 173,
779
  "ul": 461,
780
  "um": 500,
781
  "um</w>": 743,
 
793
  "use</w>": 991,
794
  "used</w>": 701,
795
  "v": 61,
796
+ "v</w>": 196,
797
  "ve": 910,
798
  "ve</w>": 371,
799
  "ved</w>": 503,
 
809
  "vision</w>": 873,
810
  "vo": 852,
811
  "w": 62,
812
+ "w</w>": 181,
813
  "wa": 464,
814
  "war": 768,
815
  "war</w>": 866,
 
842
  "x": 63,
843
  "x</w>": 184,
844
  "y": 64,
845
+ "y</w>": 169,
846
  "year</w>": 789,
847
  "years</w>": 845,
848
  "ying</w>": 868,
 
850
  "yp": 870,
851
  "ys</w>": 711,
852
  "z": 65,
853
+ "z</w>": 185,
854
  "zed</w>": 973,
855
  "|": 66,
856
+ "|</w>": 272,
857
  "}": 67,
858
  "}</w>": 285,
859
  "~": 68,
860
+ "~</w>": 182,
861
  "¡": 69,
862
+ "¡</w>": 192,
863
  "¢": 70,
864
+ "¢</w>": 234,
865
  "£": 71,
866
+ "£</w>": 237,
867
  "¤": 72,
868
+ "¤</w>": 248,
869
  "¥": 73,
870
+ "¥</w>": 265,
871
  "¦": 74,
872
+ "¦</w>": 230,
873
  "§": 75,
874
+ "§</w>": 251,
875
  "¨": 76,
876
+ "¨</w>": 219,
877
  "©": 77,
878
  "©</w>": 200,
879
  "ª": 78,
880
+ "ª</w>": 209,
881
  "«": 79,
882
+ "«</w>": 247,
883
  "¬": 80,
884
+ "¬</w>": 227,
885
  "®": 81,
886
+ "®</w>": 213,
887
  "¯": 82,
888
+ "¯</w>": 218,
889
  "°": 83,
890
+ "°</w>": 225,
891
  "±": 84,
892
+ "±</w>": 207,
893
  "²": 85,
894
+ "²</w>": 226,
895
  "³": 86,
896
+ "³</w>": 222,
897
  "´": 87,
898
+ "´</w>": 253,
899
  "µ": 88,
900
+ "µ</w>": 228,
901
  "¶": 89,
902
+ "¶</w>": 260,
903
  "·": 90,
904
+ "·</w>": 194,
905
  "¸": 91,
906
+ "¸</w>": 208,
907
  "¹": 92,
908
+ "¹</w>": 206,
909
  "º": 93,
910
+ "º</w>": 263,
911
  "»": 94,
912
+ "»</w>": 245,
913
  "¼": 95,
914
+ "¼</w>": 236,
915
  "½": 96,
916
+ "½</w>": 212,
917
  "¾": 97,
918
+ "¾</w>": 249,
919
  "¿": 98,
920
+ "¿</w>": 223,
921
  "Â": 99,
922
  "Ã": 100,
923
  "Ä": 101,
 
956
  "ì": 131,
957
  "ï": 132,
958
  "Ģ": 133,
959
+ "Ģ</w>": 202,
960
  "ģ": 134,
961
+ "ģ</w>": 232,
962
  "Ĥ": 135,
963
+ "Ĥ</w>": 211,
964
  "ĥ": 136,
965
  "ĥ</w>": 233,
966
  "Ħ": 137,
967
+ "Ħ</w>": 199,
968
  "ħ": 138,
969
+ "ħ</w>": 224,
970
  "Ĩ": 139,
971
+ "Ĩ</w>": 252,
972
  "ĩ": 140,
973
+ "ĩ</w>": 203,
974
  "Ī": 141,
975
+ "Ī</w>": 221,
976
  "ī": 142,
977
+ "ī</w>": 201,
978
  "Ĭ": 143,
979
+ "Ĭ</w>": 195,
980
  "ĭ": 144,
981
+ "ĭ</w>": 274,
982
  "Į": 145,
983
+ "Į</w>": 258,
984
  "į": 146,
985
+ "į</w>": 240,
986
  "İ": 147,
987
+ "İ</w>": 290,
988
  "ı": 148,
989
+ "ı</w>": 244,
990
  "IJ": 149,
991
+ "IJ</w>": 257,
992
  "ij": 150,
993
+ "ij</w>": 229,
994
  "Ĵ": 151,
995
+ "Ĵ</w>": 214,
996
  "ĵ": 152,
997
+ "ĵ</w>": 198,
998
  "Ķ": 153,
999
+ "Ķ</w>": 242,
1000
  "ķ": 154,
1001
+ "ķ</w>": 282,
1002
  "ĸ": 155,
1003
+ "ĸ</w>": 250,
1004
  "Ĺ": 156,
1005
+ "Ĺ</w>": 255,
1006
  "ĺ": 157,
1007
+ "ĺ</w>": 215,
1008
  "Ļ": 158,
1009
+ "Ļ</w>": 210,
1010
  "ļ": 159,
1011
+ "ļ</w>": 243,
1012
  "Ľ": 160,
1013
+ "Ľ</w>": 205,
1014
  "ľ": 161,
1015
+ "ľ</w>": 204,
1016
  "Ŀ": 162,
1017
+ "Ŀ</w>": 259,
1018
  "ŀ": 163,
1019
+ "ŀ</w>": 241,
1020
  "Ł": 164,
1021
+ "Ł</w>": 256,
1022
  "ł": 165,
1023
+ "ł</w>": 261,
1024
  "Ń": 166,
1025
+ "Ń</w>": 193
1026
  }