hf-transformers-bot commited on
Commit
e41a15f
·
verified ·
1 Parent(s): 4a20306

Update tiny models for CLIPForImageClassification

Browse files
Files changed (5) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. preprocessor_config.json +17 -0
  4. tokenizer.json +128 -128
  5. vocab.json +128 -128
config.json CHANGED
@@ -24,7 +24,7 @@
24
  "vocab_size": 1024
25
  },
26
  "torch_dtype": "float32",
27
- "transformers_version": "4.38.0.dev0",
28
  "vision_config": {
29
  "attention_dropout": 0.1,
30
  "dropout": 0.1,
 
24
  "vocab_size": 1024
25
  },
26
  "torch_dtype": "float32",
27
+ "transformers_version": "4.40.0.dev0",
28
  "vision_config": {
29
  "attention_dropout": 0.1,
30
  "dropout": 0.1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c2acb7ba6fad9103ca33adac0f1ee849bdd71fbfeb3bb363e2718fd457a063
3
  size 90104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53c70c5641d0e8431e34cb652fa9edf7b692116a841ee133a02b471c103f115
3
  size 90104
preprocessor_config.json CHANGED
@@ -1,4 +1,21 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "crop_size": {
3
  "height": 30,
4
  "width": 30
 
1
  {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_center_crop",
8
+ "crop_size",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_convert_rgb",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
  "crop_size": {
20
  "height": 30,
21
  "width": 30
tokenizer.json CHANGED
@@ -254,137 +254,137 @@
254
  "Ł": 164,
255
  "ł": 165,
256
  "Ń": 166,
257
- "i</w>": 167,
258
- "s</w>": 168,
259
- "l</w>": 169,
260
- "t</w>": 170,
261
- "h</w>": 171,
262
- "y</w>": 172,
263
- "d</w>": 173,
264
- "a</w>": 174,
265
- "o</w>": 175,
266
  "n</w>": 176,
267
- "k</w>": 177,
268
- "©</w>": 178,
269
- "e</w>": 179,
270
- "b</w>": 180,
271
- "g</w>": 181,
272
- "r</w>": 182,
273
- "f</w>": 183,
274
- "x</w>": 184,
275
- "v</w>": 185,
276
- "Ĺ</w>": 186,
277
- "º</w>": 187,
278
- "m</w>": 188,
279
- "w</w>": 189,
280
- "ĺ</w>": 190,
281
- "u</w>": 191,
282
- "²</w>": 192,
283
- "c</w>": 193,
284
- "Ĥ</w>": 194,
285
- "Ľ</w>": 195,
286
  "p</w>": 196,
287
- ".</w>": 197,
288
- "µ</w>": 198,
289
- "Ń</w>": 199,
290
- "></w>": 200,
291
- "ĩ</w>": 201,
292
- "£</w>": 202,
293
- "z</w>": 203,
294
- "«</w>": 204,
295
- "»</w>": 205,
296
- "į</w>": 206,
297
- "¢</w>": 207,
298
- "ī</w>": 208,
299
- "j</w>": 209,
300
- "q</w>": 210,
301
- "§</w>": 211,
302
- "¡</w>": 212,
303
- "¾</w>": 213,
304
- "Į</w>": 214,
305
- "³</w>": 215,
306
- "ģ</w>": 216,
307
- "¿</w>": 217,
308
- "ĵ</w>": 218,
309
- "#</w>": 219,
310
- "IJ</w>": 220,
311
- "Ĩ</w>": 221,
312
- "¤</w>": 222,
313
- "Ł</w>": 223,
314
- "°</w>": 224,
315
- "·</w>": 225,
316
- "¹</w>": 226,
317
- "¸</w>": 227,
318
- "ŀ</w>": 228,
319
- "¥</w>": 229,
320
- "ł</w>": 230,
321
- "ª</w>": 231,
322
- "}</w>": 232,
323
- "Ŀ</w>": 233,
324
- "¯</w>": 234,
325
- "ı</w>": 235,
326
- "ķ</w>": 236,
327
- "¨</w>": 237,
328
  "Ħ</w>": 238,
329
- "ĭ</w>": 239,
330
- "ħ</w>": 240,
331
- "İ</w>": 241,
332
- "¦</w>": 242,
333
- "ĥ</w>": 243,
334
- "Ĭ</w>": 244,
335
- "Ī</w>": 245,
336
- "Ļ</w>": 246,
337
- "¼</w>": 247,
338
- "Ķ</w>": 248,
339
- "`</w>": 249,
340
- "ĸ</w>": 250,
341
- "±</w>": 251,
342
- "ij</w>": 252,
343
- "´</w>": 253,
344
- "@</w>": 254,
345
- "Ĵ</w>": 255,
346
- ",</w>": 256,
347
- ":</w>": 257,
348
- "*</w>": 258,
349
- "¬</w>": 259,
350
- "Ģ</w>": 260,
351
- "'</w>": 261,
352
- "_</w>": 262,
353
- "ľ</w>": 263,
354
- "½</w>": 264,
355
- ")</w>": 265,
356
- "®</w>": 266,
357
- "\"</w>": 267,
358
- "~</w>": 268,
359
- "5</w>": 269,
360
- "7</w>": 270,
361
- "%</w>": 271,
362
- "-</w>": 272,
363
- "]</w>": 273,
364
- "!</w>": 274,
365
- "¶</w>": 275,
366
- ";</w>": 276,
367
- "/</w>": 277,
368
- "+</w>": 278,
369
- "=</w>": 279,
370
- "4</w>": 280,
371
- "(</w>": 281,
372
- "^</w>": 282,
373
- "6</w>": 283,
374
- "8</w>": 284,
375
- "&</w>": 285,
376
- "\\</w>": 286,
377
- "3</w>": 287,
378
- "0</w>": 288,
379
- "ļ</w>": 289,
380
- "$</w>": 290,
381
- "[</w>": 291,
382
- "9</w>": 292,
383
- "1</w>": 293,
384
- "|</w>": 294,
385
- "<</w>": 295,
386
- "?</w>": 296,
387
- "2</w>": 297,
388
  "th": 298,
389
  "the</w>": 299,
390
  "in": 300,
 
254
  "Ł": 164,
255
  "ł": 165,
256
  "Ń": 166,
257
+ "e</w>": 167,
258
+ "r</w>": 168,
259
+ "s</w>": 169,
260
+ "d</w>": 170,
261
+ "l</w>": 171,
262
+ "a</w>": 172,
263
+ "y</w>": 173,
264
+ "t</w>": 174,
265
+ "g</w>": 175,
266
  "n</w>": 176,
267
+ "c</w>": 177,
268
+ "h</w>": 178,
269
+ "b</w>": 179,
270
+ "ģ</w>": 180,
271
+ "f</w>": 181,
272
+ "u</w>": 182,
273
+ "k</w>": 183,
274
+ "m</w>": 184,
275
+ "i</w>": 185,
276
+ "ĩ</w>": 186,
277
+ "w</w>": 187,
278
+ "o</w>": 188,
279
+ "Ń</w>": 189,
280
+ "µ</w>": 190,
281
+ "v</w>": 191,
282
+ "j</w>": 192,
283
+ "z</w>": 193,
284
+ "¦</w>": 194,
285
+ "¨</w>": 195,
286
  "p</w>": 196,
287
+ "¢</w>": 197,
288
+ "ij</w>": 198,
289
+ "ĵ</w>": 199,
290
+ "©</w>": 200,
291
+ "¡</w>": 201,
292
+ "ĥ</w>": 202,
293
+ "ĺ</w>": 203,
294
+ "į</w>": 204,
295
+ "¹</w>": 205,
296
+ "¤</w>": 206,
297
+ "IJ</w>": 207,
298
+ "x</w>": 208,
299
+ "^</w>": 209,
300
+ "#</w>": 210,
301
+ "£</w>": 211,
302
+ "Ģ</w>": 212,
303
+ "Ļ</w>": 213,
304
+ "ĸ</w>": 214,
305
+ "!</w>": 215,
306
+ "Ĩ</w>": 216,
307
+ "¸</w>": 217,
308
+ "±</w>": 218,
309
+ "Ĥ</w>": 219,
310
+ "«</w>": 220,
311
+ "ı</w>": 221,
312
+ "Ĭ</w>": 222,
313
+ "¯</w>": 223,
314
+ "³</w>": 224,
315
+ "Ĵ</w>": 225,
316
+ "°</w>": 226,
317
+ "ī</w>": 227,
318
+ "¾</w>": 228,
319
+ "|</w>": 229,
320
+ "º</w>": 230,
321
+ "¶</w>": 231,
322
+ "»</w>": 232,
323
+ "Ĺ</w>": 233,
324
+ "Ķ</w>": 234,
325
+ "<</w>": 235,
326
+ "¥</w>": 236,
327
+ "ķ</w>": 237,
328
  "Ħ</w>": 238,
329
+ "ļ</w>": 239,
330
+ "-</w>": 240,
331
+ "ľ</w>": 241,
332
+ "·</w>": 242,
333
+ "ĭ</w>": 243,
334
+ "Ł</w>": 244,
335
+ "@</w>": 245,
336
+ "´</w>": 246,
337
+ "ħ</w>": 247,
338
+ "Ī</w>": 248,
339
+ "Į</w>": 249,
340
+ "?</w>": 250,
341
+ "¼</w>": 251,
342
+ "ł</w>": 252,
343
+ "Ŀ</w>": 253,
344
+ "ŀ</w>": 254,
345
+ "Ľ</w>": 255,
346
+ "½</w>": 256,
347
+ "²</w>": 257,
348
+ ".</w>": 258,
349
+ "ª</w>": 259,
350
+ "®</w>": 260,
351
+ "1</w>": 261,
352
+ "q</w>": 262,
353
+ "¿</w>": 263,
354
+ "]</w>": 264,
355
+ "6</w>": 265,
356
+ "~</w>": 266,
357
+ "%</w>": 267,
358
+ "'</w>": 268,
359
+ "§</w>": 269,
360
+ "*</w>": 270,
361
+ "[</w>": 271,
362
+ "7</w>": 272,
363
+ "$</w>": 273,
364
+ "¬</w>": 274,
365
+ "`</w>": 275,
366
+ "/</w>": 276,
367
+ "+</w>": 277,
368
+ "8</w>": 278,
369
+ "5</w>": 279,
370
+ "></w>": 280,
371
+ "=</w>": 281,
372
+ "3</w>": 282,
373
+ "9</w>": 283,
374
+ "0</w>": 284,
375
+ "\\</w>": 285,
376
+ "\"</w>": 286,
377
+ ";</w>": 287,
378
+ "İ</w>": 288,
379
+ "(</w>": 289,
380
+ ")</w>": 290,
381
+ "_</w>": 291,
382
+ "4</w>": 292,
383
+ ",</w>": 293,
384
+ "&</w>": 294,
385
+ "2</w>": 295,
386
+ "}</w>": 296,
387
+ ":</w>": 297,
388
  "th": 298,
389
  "the</w>": 299,
390
  "in": 300,
vocab.json CHANGED
@@ -1,91 +1,91 @@
1
  {
2
  "!": 2,
3
- "!</w>": 274,
4
  "\"": 3,
5
- "\"</w>": 267,
6
  "#": 4,
7
- "#</w>": 219,
8
  "$": 5,
9
- "$</w>": 290,
10
  "%": 6,
11
- "%</w>": 271,
12
  "&": 7,
13
- "&</w>": 285,
14
  "'": 8,
15
- "'</w>": 261,
16
  "'s</w>": 363,
17
  "(": 9,
18
- "(</w>": 281,
19
  ")": 10,
20
- ")</w>": 265,
21
  "*": 11,
22
- "*</w>": 258,
23
  "+": 12,
24
- "+</w>": 278,
25
  ",": 13,
26
- ",</w>": 256,
27
  ",@</w>": 622,
28
  "-": 14,
29
- "-</w>": 272,
30
  "-@</w>": 353,
31
  ".": 15,
32
- ".</w>": 197,
33
  ".@</w>": 569,
34
  "/": 16,
35
- "/</w>": 277,
36
  "0": 17,
37
- "0</w>": 288,
38
  "1": 18,
39
- "1</w>": 293,
40
  "2": 19,
41
- "2</w>": 297,
42
  "3": 20,
43
- "3</w>": 287,
44
  "4": 21,
45
- "4</w>": 280,
46
  "5": 22,
47
- "5</w>": 269,
48
  "6": 23,
49
- "6</w>": 283,
50
  "7": 24,
51
- "7</w>": 270,
52
  "8": 25,
53
- "8</w>": 284,
54
  "9": 26,
55
- "9</w>": 292,
56
  ":": 27,
57
- ":</w>": 257,
58
  ";": 28,
59
- ";</w>": 276,
60
  "<": 29,
61
- "<</w>": 295,
62
  "<|endoftext|>": 1,
63
  "<|startoftext|>": 0,
64
  "=": 30,
65
- "=</w>": 279,
66
  ">": 31,
67
- "></w>": 200,
68
  "?": 32,
69
- "?</w>": 296,
70
  "@": 33,
71
  "@,@</w>": 623,
72
  "@-@</w>": 354,
73
  "@.@</w>": 570,
74
- "@</w>": 254,
75
  "[": 34,
76
- "[</w>": 291,
77
  "\\": 35,
78
- "\\</w>": 286,
79
  "]": 36,
80
- "]</w>": 273,
81
  "^": 37,
82
- "^</w>": 282,
83
  "_": 38,
84
- "_</w>": 262,
85
  "`": 39,
86
- "`</w>": 249,
87
  "a": 40,
88
- "a</w>": 174,
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>": 180,
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>": 193,
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>": 173,
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>": 179,
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>": 183,
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>": 181,
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>": 171,
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>": 167,
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>": 209,
442
  "jo": 585,
443
  "joh": 941,
444
  "ju": 619,
445
  "k": 50,
446
- "k</w>": 177,
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>": 169,
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>": 188,
485
  "ma": 365,
486
  "made</w>": 794,
487
  "man": 444,
@@ -527,7 +527,7 @@
527
  "num": 763,
528
  "number</w>": 924,
529
  "o": 54,
530
- "o</w>": 175,
531
  "ob": 909,
532
  "oc": 511,
533
  "od</w>": 825,
@@ -604,10 +604,10 @@
604
  "pu": 485,
605
  "publi": 728,
606
  "q": 56,
607
- "q</w>": 210,
608
  "qu": 431,
609
  "r": 57,
610
- "r</w>": 182,
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>": 170,
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>": 191,
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>": 185,
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>": 189,
813
  "wa": 464,
814
  "war": 768,
815
  "war</w>": 866,
@@ -840,9 +840,9 @@
840
  "writ": 722,
841
  "ws</w>": 953,
842
  "x": 63,
843
- "x</w>": 184,
844
  "y": 64,
845
- "y</w>": 172,
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>": 203,
854
  "zed</w>": 973,
855
  "|": 66,
856
- "|</w>": 294,
857
  "}": 67,
858
- "}</w>": 232,
859
  "~": 68,
860
- "~</w>": 268,
861
  "¡": 69,
862
- "¡</w>": 212,
863
  "¢": 70,
864
- "¢</w>": 207,
865
  "£": 71,
866
- "£</w>": 202,
867
  "¤": 72,
868
- "¤</w>": 222,
869
  "¥": 73,
870
- "¥</w>": 229,
871
  "¦": 74,
872
- "¦</w>": 242,
873
  "§": 75,
874
- "§</w>": 211,
875
  "¨": 76,
876
- "¨</w>": 237,
877
  "©": 77,
878
- "©</w>": 178,
879
  "ª": 78,
880
- "ª</w>": 231,
881
  "«": 79,
882
- "«</w>": 204,
883
  "¬": 80,
884
- "¬</w>": 259,
885
  "®": 81,
886
- "®</w>": 266,
887
  "¯": 82,
888
- "¯</w>": 234,
889
  "°": 83,
890
- "°</w>": 224,
891
  "±": 84,
892
- "±</w>": 251,
893
  "²": 85,
894
- "²</w>": 192,
895
  "³": 86,
896
- "³</w>": 215,
897
  "´": 87,
898
- "´</w>": 253,
899
  "µ": 88,
900
- "µ</w>": 198,
901
  "¶": 89,
902
- "¶</w>": 275,
903
  "·": 90,
904
- "·</w>": 225,
905
  "¸": 91,
906
- "¸</w>": 227,
907
  "¹": 92,
908
- "¹</w>": 226,
909
  "º": 93,
910
- "º</w>": 187,
911
  "»": 94,
912
- "»</w>": 205,
913
  "¼": 95,
914
- "¼</w>": 247,
915
  "½": 96,
916
- "½</w>": 264,
917
  "¾": 97,
918
- "¾</w>": 213,
919
  "¿": 98,
920
- "¿</w>": 217,
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>": 260,
960
  "ģ": 134,
961
- "ģ</w>": 216,
962
  "Ĥ": 135,
963
- "Ĥ</w>": 194,
964
  "ĥ": 136,
965
- "ĥ</w>": 243,
966
  "Ħ": 137,
967
  "Ħ</w>": 238,
968
  "ħ": 138,
969
- "ħ</w>": 240,
970
  "Ĩ": 139,
971
- "Ĩ</w>": 221,
972
  "ĩ": 140,
973
- "ĩ</w>": 201,
974
  "Ī": 141,
975
- "Ī</w>": 245,
976
  "ī": 142,
977
- "ī</w>": 208,
978
  "Ĭ": 143,
979
- "Ĭ</w>": 244,
980
  "ĭ": 144,
981
- "ĭ</w>": 239,
982
  "Į": 145,
983
- "Į</w>": 214,
984
  "į": 146,
985
- "į</w>": 206,
986
  "İ": 147,
987
- "İ</w>": 241,
988
  "ı": 148,
989
- "ı</w>": 235,
990
  "IJ": 149,
991
- "IJ</w>": 220,
992
  "ij": 150,
993
- "ij</w>": 252,
994
  "Ĵ": 151,
995
- "Ĵ</w>": 255,
996
  "ĵ": 152,
997
- "ĵ</w>": 218,
998
  "Ķ": 153,
999
- "Ķ</w>": 248,
1000
  "ķ": 154,
1001
- "ķ</w>": 236,
1002
  "ĸ": 155,
1003
- "ĸ</w>": 250,
1004
  "Ĺ": 156,
1005
- "Ĺ</w>": 186,
1006
  "ĺ": 157,
1007
- "ĺ</w>": 190,
1008
  "Ļ": 158,
1009
- "Ļ</w>": 246,
1010
  "ļ": 159,
1011
- "ļ</w>": 289,
1012
  "Ľ": 160,
1013
- "Ľ</w>": 195,
1014
  "ľ": 161,
1015
- "ľ</w>": 263,
1016
  "Ŀ": 162,
1017
- "Ŀ</w>": 233,
1018
  "ŀ": 163,
1019
- "ŀ</w>": 228,
1020
  "Ł": 164,
1021
- "Ł</w>": 223,
1022
  "ł": 165,
1023
- "ł</w>": 230,
1024
  "Ń": 166,
1025
- "Ń</w>": 199
1026
  }
 
1
  {
2
  "!": 2,
3
+ "!</w>": 215,
4
  "\"": 3,
5
+ "\"</w>": 286,
6
  "#": 4,
7
+ "#</w>": 210,
8
  "$": 5,
9
+ "$</w>": 273,
10
  "%": 6,
11
+ "%</w>": 267,
12
  "&": 7,
13
+ "&</w>": 294,
14
  "'": 8,
15
+ "'</w>": 268,
16
  "'s</w>": 363,
17
  "(": 9,
18
+ "(</w>": 289,
19
  ")": 10,
20
+ ")</w>": 290,
21
  "*": 11,
22
+ "*</w>": 270,
23
  "+": 12,
24
+ "+</w>": 277,
25
  ",": 13,
26
+ ",</w>": 293,
27
  ",@</w>": 622,
28
  "-": 14,
29
+ "-</w>": 240,
30
  "-@</w>": 353,
31
  ".": 15,
32
+ ".</w>": 258,
33
  ".@</w>": 569,
34
  "/": 16,
35
+ "/</w>": 276,
36
  "0": 17,
37
+ "0</w>": 284,
38
  "1": 18,
39
+ "1</w>": 261,
40
  "2": 19,
41
+ "2</w>": 295,
42
  "3": 20,
43
+ "3</w>": 282,
44
  "4": 21,
45
+ "4</w>": 292,
46
  "5": 22,
47
+ "5</w>": 279,
48
  "6": 23,
49
+ "6</w>": 265,
50
  "7": 24,
51
+ "7</w>": 272,
52
  "8": 25,
53
+ "8</w>": 278,
54
  "9": 26,
55
+ "9</w>": 283,
56
  ":": 27,
57
+ ":</w>": 297,
58
  ";": 28,
59
+ ";</w>": 287,
60
  "<": 29,
61
+ "<</w>": 235,
62
  "<|endoftext|>": 1,
63
  "<|startoftext|>": 0,
64
  "=": 30,
65
+ "=</w>": 281,
66
  ">": 31,
67
+ "></w>": 280,
68
  "?": 32,
69
+ "?</w>": 250,
70
  "@": 33,
71
  "@,@</w>": 623,
72
  "@-@</w>": 354,
73
  "@.@</w>": 570,
74
+ "@</w>": 245,
75
  "[": 34,
76
+ "[</w>": 271,
77
  "\\": 35,
78
+ "\\</w>": 285,
79
  "]": 36,
80
+ "]</w>": 264,
81
  "^": 37,
82
+ "^</w>": 209,
83
  "_": 38,
84
+ "_</w>": 291,
85
  "`": 39,
86
+ "`</w>": 275,
87
  "a": 40,
88
+ "a</w>": 172,
89
  "ab": 408,
90
  "able</w>": 675,
91
  "about</w>": 721,
 
158
  "au": 448,
159
  "ause</w>": 997,
160
  "b": 41,
161
+ "b</w>": 179,
162
  "ba": 687,
163
  "back</w>": 992,
164
  "bar": 821,
 
194
  "but</w>": 499,
195
  "by</w>": 369,
196
  "c": 42,
197
+ "c</w>": 177,
198
  "ca": 394,
199
  "cal": 820,
200
  "called</w>": 1014,
 
243
  "cul": 881,
244
  "cur": 990,
245
  "d": 43,
246
+ "d</w>": 170,
247
  "da": 497,
248
  "day</w>": 755,
249
  "de": 352,
 
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
  "ever</w>": 754,
327
  "ex": 417,
328
  "f": 45,
329
+ "f</w>": 181,
330
  "fa": 630,
331
  "fac": 893,
332
  "fe": 484,
 
355
  "ft</w>": 707,
356
  "fu": 665,
357
  "g": 46,
358
+ "g</w>": 175,
359
  "ga": 631,
360
  "game</w>": 697,
361
  "gan</w>": 835,
 
378
  "gs</w>": 975,
379
  "gu": 426,
380
  "h": 47,
381
+ "h</w>": 178,
382
  "ha": 367,
383
  "had</w>": 459,
384
  "har": 971,
 
400
  "however</w>": 867,
401
  "hu": 993,
402
  "i": 48,
403
+ "i</w>": 185,
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>": 192,
442
  "jo": 585,
443
  "joh": 941,
444
  "ju": 619,
445
  "k": 50,
446
+ "k</w>": 183,
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>": 171,
456
  "la": 348,
457
  "lan": 606,
458
  "land</w>": 561,
 
481
  "lu": 432,
482
  "ly</w>": 342,
483
  "m": 52,
484
+ "m</w>": 184,
485
  "ma": 365,
486
  "made</w>": 794,
487
  "man": 444,
 
527
  "num": 763,
528
  "number</w>": 924,
529
  "o": 54,
530
+ "o</w>": 188,
531
  "ob": 909,
532
  "oc": 511,
533
  "od</w>": 825,
 
604
  "pu": 485,
605
  "publi": 728,
606
  "q": 56,
607
+ "q</w>": 262,
608
  "qu": 431,
609
  "r": 57,
610
+ "r</w>": 168,
611
  "ra": 355,
612
  "ran": 523,
613
  "re": 304,
 
629
  "ru": 419,
630
  "ry</w>": 885,
631
  "s": 58,
632
+ "s</w>": 169,
633
  "sa": 510,
634
  "sc": 414,
635
  "sch": 775,
 
705
  "sur": 642,
706
  "sy": 673,
707
  "t": 59,
708
+ "t</w>": 174,
709
  "ta": 438,
710
  "tain</w>": 1010,
711
  "te": 544,
 
775
  "two</w>": 545,
776
  "ty</w>": 584,
777
  "u": 60,
778
+ "u</w>": 182,
779
  "ul": 461,
780
  "um": 500,
781
  "um</w>": 743,
 
793
  "use</w>": 991,
794
  "used</w>": 701,
795
  "v": 61,
796
+ "v</w>": 191,
797
  "ve": 910,
798
  "ve</w>": 371,
799
  "ved</w>": 503,
 
809
  "vision</w>": 873,
810
  "vo": 852,
811
  "w": 62,
812
+ "w</w>": 187,
813
  "wa": 464,
814
  "war": 768,
815
  "war</w>": 866,
 
840
  "writ": 722,
841
  "ws</w>": 953,
842
  "x": 63,
843
+ "x</w>": 208,
844
  "y": 64,
845
+ "y</w>": 173,
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>": 193,
854
  "zed</w>": 973,
855
  "|": 66,
856
+ "|</w>": 229,
857
  "}": 67,
858
+ "}</w>": 296,
859
  "~": 68,
860
+ "~</w>": 266,
861
  "¡": 69,
862
+ "¡</w>": 201,
863
  "¢": 70,
864
+ "¢</w>": 197,
865
  "£": 71,
866
+ "£</w>": 211,
867
  "¤": 72,
868
+ "¤</w>": 206,
869
  "¥": 73,
870
+ "¥</w>": 236,
871
  "¦": 74,
872
+ "¦</w>": 194,
873
  "§": 75,
874
+ "§</w>": 269,
875
  "¨": 76,
876
+ "¨</w>": 195,
877
  "©": 77,
878
+ "©</w>": 200,
879
  "ª": 78,
880
+ "ª</w>": 259,
881
  "«": 79,
882
+ "«</w>": 220,
883
  "¬": 80,
884
+ "¬</w>": 274,
885
  "®": 81,
886
+ "®</w>": 260,
887
  "¯": 82,
888
+ "¯</w>": 223,
889
  "°": 83,
890
+ "°</w>": 226,
891
  "±": 84,
892
+ "±</w>": 218,
893
  "²": 85,
894
+ "²</w>": 257,
895
  "³": 86,
896
+ "³</w>": 224,
897
  "´": 87,
898
+ "´</w>": 246,
899
  "µ": 88,
900
+ "µ</w>": 190,
901
  "¶": 89,
902
+ "¶</w>": 231,
903
  "·": 90,
904
+ "·</w>": 242,
905
  "¸": 91,
906
+ "¸</w>": 217,
907
  "¹": 92,
908
+ "¹</w>": 205,
909
  "º": 93,
910
+ "º</w>": 230,
911
  "»": 94,
912
+ "»</w>": 232,
913
  "¼": 95,
914
+ "¼</w>": 251,
915
  "½": 96,
916
+ "½</w>": 256,
917
  "¾": 97,
918
+ "¾</w>": 228,
919
  "¿": 98,
920
+ "¿</w>": 263,
921
  "Â": 99,
922
  "Ã": 100,
923
  "Ä": 101,
 
956
  "ì": 131,
957
  "ï": 132,
958
  "Ģ": 133,
959
+ "Ģ</w>": 212,
960
  "ģ": 134,
961
+ "ģ</w>": 180,
962
  "Ĥ": 135,
963
+ "Ĥ</w>": 219,
964
  "ĥ": 136,
965
+ "ĥ</w>": 202,
966
  "Ħ": 137,
967
  "Ħ</w>": 238,
968
  "ħ": 138,
969
+ "ħ</w>": 247,
970
  "Ĩ": 139,
971
+ "Ĩ</w>": 216,
972
  "ĩ": 140,
973
+ "ĩ</w>": 186,
974
  "Ī": 141,
975
+ "Ī</w>": 248,
976
  "ī": 142,
977
+ "ī</w>": 227,
978
  "Ĭ": 143,
979
+ "Ĭ</w>": 222,
980
  "ĭ": 144,
981
+ "ĭ</w>": 243,
982
  "Į": 145,
983
+ "Į</w>": 249,
984
  "į": 146,
985
+ "į</w>": 204,
986
  "İ": 147,
987
+ "İ</w>": 288,
988
  "ı": 148,
989
+ "ı</w>": 221,
990
  "IJ": 149,
991
+ "IJ</w>": 207,
992
  "ij": 150,
993
+ "ij</w>": 198,
994
  "Ĵ": 151,
995
+ "Ĵ</w>": 225,
996
  "ĵ": 152,
997
+ "ĵ</w>": 199,
998
  "Ķ": 153,
999
+ "Ķ</w>": 234,
1000
  "ķ": 154,
1001
+ "ķ</w>": 237,
1002
  "ĸ": 155,
1003
+ "ĸ</w>": 214,
1004
  "Ĺ": 156,
1005
+ "Ĺ</w>": 233,
1006
  "ĺ": 157,
1007
+ "ĺ</w>": 203,
1008
  "Ļ": 158,
1009
+ "Ļ</w>": 213,
1010
  "ļ": 159,
1011
+ "ļ</w>": 239,
1012
  "Ľ": 160,
1013
+ "Ľ</w>": 255,
1014
  "ľ": 161,
1015
+ "ľ</w>": 241,
1016
  "Ŀ": 162,
1017
+ "Ŀ</w>": 253,
1018
  "ŀ": 163,
1019
+ "ŀ</w>": 254,
1020
  "Ł": 164,
1021
+ "Ł</w>": 244,
1022
  "ł": 165,
1023
+ "ł</w>": 252,
1024
  "Ń": 166,
1025
+ "Ń</w>": 189
1026
  }