Hugging Face's logo

yujianglu
/
donut-demo

Image-Text-to-Text
Transformers
PyTorch
vision-encoder-decoder
Inference Endpoints
Model card Files Community
yujianglu commited on
Commit
774095a
•
1 Parent(s): 609b937

Training done

Browse files
Files changed (2) hide show
  1. added_tokens.json +86 -85
  2. tokenizer.json +94 -85
added_tokens.json CHANGED
@@ -1,90 +1,91 @@
1
  {
2
- "</s_0>": 57600,
3
- "</s_10>": 57596,
4
- "</s_11>": 57594,
5
- "</s_12>": 57592,
6
- "</s_13>": 57590,
7
- "</s_14>": 57588,
8
- "</s_15>": 57586,
9
- "</s_16>": 57602,
10
- "</s_17>": 57584,
11
- "</s_18>": 57582,
12
- "</s_19>": 57580,
13
- "</s_1>": 57598,
14
- "</s_20>": 57578,
15
- "</s_21>": 57576,
16
- "</s_22>": 57574,
17
- "</s_23>": 57572,
18
- "</s_24>": 57570,
19
- "</s_25>": 57568,
20
- "</s_26>": 57566,
21
- "</s_27>": 57564,
22
- "</s_28>": 57562,
23
- "</s_29>": 57560,
24
- "</s_2>": 57608,
25
- "</s_30>": 57558,
26
- "</s_31>": 57556,
27
- "</s_32>": 57554,
28
- "</s_33>": 57552,
29
- "</s_34>": 57550,
30
- "</s_35>": 57548,
31
- "</s_36>": 57546,
32
- "</s_37>": 57544,
33
- "</s_38>": 57542,
34
- "</s_39>": 57540,
35
- "</s_3>": 57606,
36
- "</s_40>": 57538,
37
- "</s_41>": 57536,
38
- "</s_42>": 57534,
39
- "</s_4>": 57604,
40
- "</s_5>": 57532,
41
- "</s_6>": 57530,
42
- "</s_7>": 57528,
43
- "</s_8>": 57526,
44
- "<s_0>": 57599,
45
- "<s_10>": 57595,
46
- "<s_11>": 57593,
47
- "<s_12>": 57591,
48
- "<s_13>": 57589,
49
- "<s_14>": 57587,
50
- "<s_15>": 57585,
51
- "<s_16>": 57601,
52
- "<s_17>": 57583,
53
- "<s_18>": 57581,
54
- "<s_19>": 57579,
55
- "<s_1>": 57597,
56
- "<s_20>": 57577,
57
- "<s_21>": 57575,
58
- "<s_22>": 57573,
59
- "<s_23>": 57571,
60
- "<s_24>": 57569,
61
- "<s_25>": 57567,
62
- "<s_26>": 57565,
63
- "<s_27>": 57563,
64
- "<s_28>": 57561,
65
- "<s_29>": 57559,
66
- "<s_2>": 57607,
67
- "<s_30>": 57557,
68
- "<s_31>": 57555,
69
- "<s_32>": 57553,
70
- "<s_33>": 57551,
71
- "<s_34>": 57549,
72
- "<s_35>": 57547,
73
- "<s_36>": 57545,
74
- "<s_37>": 57543,
75
- "<s_38>": 57541,
76
- "<s_39>": 57539,
77
- "<s_3>": 57605,
78
- "<s_40>": 57537,
79
- "<s_41>": 57535,
80
- "<s_42>": 57533,
81
- "<s_4>": 57603,
82
- "<s_5>": 57531,
83
- "<s_6>": 57529,
84
- "<s_7>": 57527,
85
- "<s_8>": 57525,
86
- "<s_cord-v2>": 57609,
87
  "<s_iitcdip>": 57523,
 
88
  "<s_synthdog>": 57524,
89
  "<sep/>": 57522
90
  }
 
1
  {
2
+ "</s_0>": 57538,
3
+ "</s_10>": 57554,
4
+ "</s_11>": 57552,
5
+ "</s_12>": 57550,
6
+ "</s_13>": 57548,
7
+ "</s_14>": 57546,
8
+ "</s_15>": 57544,
9
+ "</s_16>": 57570,
10
+ "</s_17>": 57568,
11
+ "</s_18>": 57566,
12
+ "</s_19>": 57564,
13
+ "</s_1>": 57536,
14
+ "</s_20>": 57562,
15
+ "</s_21>": 57560,
16
+ "</s_22>": 57558,
17
+ "</s_23>": 57556,
18
+ "</s_24>": 57574,
19
+ "</s_25>": 57572,
20
+ "</s_26>": 57586,
21
+ "</s_27>": 57584,
22
+ "</s_28>": 57582,
23
+ "</s_29>": 57580,
24
+ "</s_2>": 57534,
25
+ "</s_30>": 57578,
26
+ "</s_31>": 57576,
27
+ "</s_32>": 57594,
28
+ "</s_33>": 57592,
29
+ "</s_34>": 57590,
30
+ "</s_35>": 57588,
31
+ "</s_36>": 57596,
32
+ "</s_37>": 57598,
33
+ "</s_38>": 57600,
34
+ "</s_39>": 57604,
35
+ "</s_3>": 57532,
36
+ "</s_40>": 57602,
37
+ "</s_4>": 57530,
38
+ "</s_5>": 57528,
39
+ "</s_6>": 57526,
40
+ "</s_8>": 57542,
41
+ "</s_9>": 57540,
42
+ "</s_answer>": 57609,
43
+ "</s_question>": 57607,
44
+ "<s_0>": 57537,
45
+ "<s_10>": 57553,
46
+ "<s_11>": 57551,
47
+ "<s_12>": 57549,
48
+ "<s_13>": 57547,
49
+ "<s_14>": 57545,
50
+ "<s_15>": 57543,
51
+ "<s_16>": 57569,
52
+ "<s_17>": 57567,
53
+ "<s_18>": 57565,
54
+ "<s_19>": 57563,
55
+ "<s_1>": 57535,
56
+ "<s_20>": 57561,
57
+ "<s_21>": 57559,
58
+ "<s_22>": 57557,
59
+ "<s_23>": 57555,
60
+ "<s_24>": 57573,
61
+ "<s_25>": 57571,
62
+ "<s_26>": 57585,
63
+ "<s_27>": 57583,
64
+ "<s_28>": 57581,
65
+ "<s_29>": 57579,
66
+ "<s_2>": 57533,
67
+ "<s_30>": 57577,
68
+ "<s_31>": 57575,
69
+ "<s_32>": 57593,
70
+ "<s_33>": 57591,
71
+ "<s_34>": 57589,
72
+ "<s_35>": 57587,
73
+ "<s_36>": 57595,
74
+ "<s_37>": 57597,
75
+ "<s_38>": 57599,
76
+ "<s_39>": 57603,
77
+ "<s_3>": 57531,
78
+ "<s_40>": 57601,
79
+ "<s_4>": 57529,
80
+ "<s_5>": 57527,
81
+ "<s_6>": 57525,
82
+ "<s_8>": 57541,
83
+ "<s_9>": 57539,
84
+ "<s_answer>": 57608,
85
+ "<s_cord-v2>": 57605,
86
+ "<s_docvqa>": 57610,
87
  "<s_iitcdip>": 57523,
88
+ "<s_question>": 57606,
89
  "<s_synthdog>": 57524,
90
  "<sep/>": 57522
91
  }
tokenizer.json CHANGED
@@ -77,7 +77,7 @@
77
  },
78
  {
79
  "id": 57525,
80
- "content": "<s_8>",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
@@ -86,7 +86,7 @@
86
  },
87
  {
88
  "id": 57526,
89
- "content": "</s_8>",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
@@ -95,7 +95,7 @@
95
  },
96
  {
97
  "id": 57527,
98
- "content": "<s_7>",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
@@ -104,7 +104,7 @@
104
  },
105
  {
106
  "id": 57528,
107
- "content": "</s_7>",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  },
114
  {
115
  "id": 57529,
116
- "content": "<s_6>",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
@@ -122,7 +122,7 @@
122
  },
123
  {
124
  "id": 57530,
125
- "content": "</s_6>",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
@@ -131,7 +131,7 @@
131
  },
132
  {
133
  "id": 57531,
134
- "content": "<s_5>",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
@@ -140,7 +140,7 @@
140
  },
141
  {
142
  "id": 57532,
143
- "content": "</s_5>",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
@@ -149,7 +149,7 @@
149
  },
150
  {
151
  "id": 57533,
152
- "content": "<s_42>",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
@@ -158,7 +158,7 @@
158
  },
159
  {
160
  "id": 57534,
161
- "content": "</s_42>",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
@@ -167,7 +167,7 @@
167
  },
168
  {
169
  "id": 57535,
170
- "content": "<s_41>",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
@@ -176,7 +176,7 @@
176
  },
177
  {
178
  "id": 57536,
179
- "content": "</s_41>",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  },
186
  {
187
  "id": 57537,
188
- "content": "<s_40>",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
@@ -194,7 +194,7 @@
194
  },
195
  {
196
  "id": 57538,
197
- "content": "</s_40>",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
@@ -203,7 +203,7 @@
203
  },
204
  {
205
  "id": 57539,
206
- "content": "<s_39>",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
@@ -212,7 +212,7 @@
212
  },
213
  {
214
  "id": 57540,
215
- "content": "</s_39>",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
@@ -221,7 +221,7 @@
221
  },
222
  {
223
  "id": 57541,
224
- "content": "<s_38>",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
@@ -230,7 +230,7 @@
230
  },
231
  {
232
  "id": 57542,
233
- "content": "</s_38>",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
@@ -239,7 +239,7 @@
239
  },
240
  {
241
  "id": 57543,
242
- "content": "<s_37>",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
@@ -248,7 +248,7 @@
248
  },
249
  {
250
  "id": 57544,
251
- "content": "</s_37>",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  },
258
  {
259
  "id": 57545,
260
- "content": "<s_36>",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
@@ -266,7 +266,7 @@
266
  },
267
  {
268
  "id": 57546,
269
- "content": "</s_36>",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
@@ -275,7 +275,7 @@
275
  },
276
  {
277
  "id": 57547,
278
- "content": "<s_35>",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
@@ -284,7 +284,7 @@
284
  },
285
  {
286
  "id": 57548,
287
- "content": "</s_35>",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
@@ -293,7 +293,7 @@
293
  },
294
  {
295
  "id": 57549,
296
- "content": "<s_34>",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
@@ -302,7 +302,7 @@
302
  },
303
  {
304
  "id": 57550,
305
- "content": "</s_34>",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
@@ -311,7 +311,7 @@
311
  },
312
  {
313
  "id": 57551,
314
- "content": "<s_33>",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
@@ -320,7 +320,7 @@
320
  },
321
  {
322
  "id": 57552,
323
- "content": "</s_33>",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  },
330
  {
331
  "id": 57553,
332
- "content": "<s_32>",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
@@ -338,7 +338,7 @@
338
  },
339
  {
340
  "id": 57554,
341
- "content": "</s_32>",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
@@ -347,7 +347,7 @@
347
  },
348
  {
349
  "id": 57555,
350
- "content": "<s_31>",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
@@ -356,7 +356,7 @@
356
  },
357
  {
358
  "id": 57556,
359
- "content": "</s_31>",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
@@ -365,7 +365,7 @@
365
  },
366
  {
367
  "id": 57557,
368
- "content": "<s_30>",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
@@ -374,7 +374,7 @@
374
  },
375
  {
376
  "id": 57558,
377
- "content": "</s_30>",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
@@ -383,7 +383,7 @@
383
  },
384
  {
385
  "id": 57559,
386
- "content": "<s_29>",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
@@ -392,7 +392,7 @@
392
  },
393
  {
394
  "id": 57560,
395
- "content": "</s_29>",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  },
402
  {
403
  "id": 57561,
404
- "content": "<s_28>",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
@@ -410,7 +410,7 @@
410
  },
411
  {
412
  "id": 57562,
413
- "content": "</s_28>",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
@@ -419,7 +419,7 @@
419
  },
420
  {
421
  "id": 57563,
422
- "content": "<s_27>",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
@@ -428,7 +428,7 @@
428
  },
429
  {
430
  "id": 57564,
431
- "content": "</s_27>",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
@@ -437,7 +437,7 @@
437
  },
438
  {
439
  "id": 57565,
440
- "content": "<s_26>",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
@@ -446,7 +446,7 @@
446
  },
447
  {
448
  "id": 57566,
449
- "content": "</s_26>",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
@@ -455,7 +455,7 @@
455
  },
456
  {
457
  "id": 57567,
458
- "content": "<s_25>",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
@@ -464,7 +464,7 @@
464
  },
465
  {
466
  "id": 57568,
467
- "content": "</s_25>",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
@@ -473,7 +473,7 @@
473
  },
474
  {
475
  "id": 57569,
476
- "content": "<s_24>",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
@@ -482,7 +482,7 @@
482
  },
483
  {
484
  "id": 57570,
485
- "content": "</s_24>",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
@@ -491,7 +491,7 @@
491
  },
492
  {
493
  "id": 57571,
494
- "content": "<s_23>",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
@@ -500,7 +500,7 @@
500
  },
501
  {
502
  "id": 57572,
503
- "content": "</s_23>",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
@@ -509,7 +509,7 @@
509
  },
510
  {
511
  "id": 57573,
512
- "content": "<s_22>",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
@@ -518,7 +518,7 @@
518
  },
519
  {
520
  "id": 57574,
521
- "content": "</s_22>",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
@@ -527,7 +527,7 @@
527
  },
528
  {
529
  "id": 57575,
530
- "content": "<s_21>",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
@@ -536,7 +536,7 @@
536
  },
537
  {
538
  "id": 57576,
539
- "content": "</s_21>",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
@@ -545,7 +545,7 @@
545
  },
546
  {
547
  "id": 57577,
548
- "content": "<s_20>",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
@@ -554,7 +554,7 @@
554
  },
555
  {
556
  "id": 57578,
557
- "content": "</s_20>",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
@@ -563,7 +563,7 @@
563
  },
564
  {
565
  "id": 57579,
566
- "content": "<s_19>",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
@@ -572,7 +572,7 @@
572
  },
573
  {
574
  "id": 57580,
575
- "content": "</s_19>",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
@@ -581,7 +581,7 @@
581
  },
582
  {
583
  "id": 57581,
584
- "content": "<s_18>",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
@@ -590,7 +590,7 @@
590
  },
591
  {
592
  "id": 57582,
593
- "content": "</s_18>",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
@@ -599,7 +599,7 @@
599
  },
600
  {
601
  "id": 57583,
602
- "content": "<s_17>",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
@@ -608,7 +608,7 @@
608
  },
609
  {
610
  "id": 57584,
611
- "content": "</s_17>",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
@@ -617,7 +617,7 @@
617
  },
618
  {
619
  "id": 57585,
620
- "content": "<s_15>",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
@@ -626,7 +626,7 @@
626
  },
627
  {
628
  "id": 57586,
629
- "content": "</s_15>",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
@@ -635,7 +635,7 @@
635
  },
636
  {
637
  "id": 57587,
638
- "content": "<s_14>",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
@@ -644,7 +644,7 @@
644
  },
645
  {
646
  "id": 57588,
647
- "content": "</s_14>",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
@@ -653,7 +653,7 @@
653
  },
654
  {
655
  "id": 57589,
656
- "content": "<s_13>",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
@@ -662,7 +662,7 @@
662
  },
663
  {
664
  "id": 57590,
665
- "content": "</s_13>",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
@@ -671,7 +671,7 @@
671
  },
672
  {
673
  "id": 57591,
674
- "content": "<s_12>",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
@@ -680,7 +680,7 @@
680
  },
681
  {
682
  "id": 57592,
683
- "content": "</s_12>",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
@@ -689,7 +689,7 @@
689
  },
690
  {
691
  "id": 57593,
692
- "content": "<s_11>",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
@@ -698,7 +698,7 @@
698
  },
699
  {
700
  "id": 57594,
701
- "content": "</s_11>",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
@@ -707,7 +707,7 @@
707
  },
708
  {
709
  "id": 57595,
710
- "content": "<s_10>",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
@@ -716,7 +716,7 @@
716
  },
717
  {
718
  "id": 57596,
719
- "content": "</s_10>",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
@@ -725,7 +725,7 @@
725
  },
726
  {
727
  "id": 57597,
728
- "content": "<s_1>",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
@@ -734,7 +734,7 @@
734
  },
735
  {
736
  "id": 57598,
737
- "content": "</s_1>",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
@@ -743,7 +743,7 @@
743
  },
744
  {
745
  "id": 57599,
746
- "content": "<s_0>",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
@@ -752,7 +752,7 @@
752
  },
753
  {
754
  "id": 57600,
755
- "content": "</s_0>",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
@@ -761,7 +761,7 @@
761
  },
762
  {
763
  "id": 57601,
764
- "content": "<s_16>",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
@@ -770,7 +770,7 @@
770
  },
771
  {
772
  "id": 57602,
773
- "content": "</s_16>",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
@@ -779,7 +779,7 @@
779
  },
780
  {
781
  "id": 57603,
782
- "content": "<s_4>",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
@@ -788,7 +788,7 @@
788
  },
789
  {
790
  "id": 57604,
791
- "content": "</s_4>",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
@@ -797,7 +797,7 @@
797
  },
798
  {
799
  "id": 57605,
800
- "content": "<s_3>",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
@@ -806,7 +806,7 @@
806
  },
807
  {
808
  "id": 57606,
809
- "content": "</s_3>",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
@@ -815,7 +815,7 @@
815
  },
816
  {
817
  "id": 57607,
818
- "content": "<s_2>",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
@@ -824,7 +824,7 @@
824
  },
825
  {
826
  "id": 57608,
827
- "content": "</s_2>",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
@@ -833,7 +833,16 @@
833
  },
834
  {
835
  "id": 57609,
836
- "content": "<s_cord-v2>",
 
 
 
 
 
 
 
 
 
837
  "single_word": false,
838
  "lstrip": false,
839
  "rstrip": false,
 
77
  },
78
  {
79
  "id": 57525,
80
+ "content": "<s_6>",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
 
86
  },
87
  {
88
  "id": 57526,
89
+ "content": "</s_6>",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
 
95
  },
96
  {
97
  "id": 57527,
98
+ "content": "<s_5>",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
 
104
  },
105
  {
106
  "id": 57528,
107
+ "content": "</s_5>",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
 
113
  },
114
  {
115
  "id": 57529,
116
+ "content": "<s_4>",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
 
122
  },
123
  {
124
  "id": 57530,
125
+ "content": "</s_4>",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
 
131
  },
132
  {
133
  "id": 57531,
134
+ "content": "<s_3>",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
 
140
  },
141
  {
142
  "id": 57532,
143
+ "content": "</s_3>",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
 
149
  },
150
  {
151
  "id": 57533,
152
+ "content": "<s_2>",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
 
158
  },
159
  {
160
  "id": 57534,
161
+ "content": "</s_2>",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
 
167
  },
168
  {
169
  "id": 57535,
170
+ "content": "<s_1>",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
 
176
  },
177
  {
178
  "id": 57536,
179
+ "content": "</s_1>",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
 
185
  },
186
  {
187
  "id": 57537,
188
+ "content": "<s_0>",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
 
194
  },
195
  {
196
  "id": 57538,
197
+ "content": "</s_0>",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
 
203
  },
204
  {
205
  "id": 57539,
206
+ "content": "<s_9>",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
 
212
  },
213
  {
214
  "id": 57540,
215
+ "content": "</s_9>",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
 
221
  },
222
  {
223
  "id": 57541,
224
+ "content": "<s_8>",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
 
230
  },
231
  {
232
  "id": 57542,
233
+ "content": "</s_8>",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
 
239
  },
240
  {
241
  "id": 57543,
242
+ "content": "<s_15>",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
 
248
  },
249
  {
250
  "id": 57544,
251
+ "content": "</s_15>",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
 
257
  },
258
  {
259
  "id": 57545,
260
+ "content": "<s_14>",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
 
266
  },
267
  {
268
  "id": 57546,
269
+ "content": "</s_14>",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
 
275
  },
276
  {
277
  "id": 57547,
278
+ "content": "<s_13>",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
 
284
  },
285
  {
286
  "id": 57548,
287
+ "content": "</s_13>",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
 
293
  },
294
  {
295
  "id": 57549,
296
+ "content": "<s_12>",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
 
302
  },
303
  {
304
  "id": 57550,
305
+ "content": "</s_12>",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
 
311
  },
312
  {
313
  "id": 57551,
314
+ "content": "<s_11>",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
 
320
  },
321
  {
322
  "id": 57552,
323
+ "content": "</s_11>",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
 
329
  },
330
  {
331
  "id": 57553,
332
+ "content": "<s_10>",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
 
338
  },
339
  {
340
  "id": 57554,
341
+ "content": "</s_10>",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
 
347
  },
348
  {
349
  "id": 57555,
350
+ "content": "<s_23>",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
 
356
  },
357
  {
358
  "id": 57556,
359
+ "content": "</s_23>",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
 
365
  },
366
  {
367
  "id": 57557,
368
+ "content": "<s_22>",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
 
374
  },
375
  {
376
  "id": 57558,
377
+ "content": "</s_22>",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
 
383
  },
384
  {
385
  "id": 57559,
386
+ "content": "<s_21>",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
 
392
  },
393
  {
394
  "id": 57560,
395
+ "content": "</s_21>",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
 
401
  },
402
  {
403
  "id": 57561,
404
+ "content": "<s_20>",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
 
410
  },
411
  {
412
  "id": 57562,
413
+ "content": "</s_20>",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
 
419
  },
420
  {
421
  "id": 57563,
422
+ "content": "<s_19>",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
 
428
  },
429
  {
430
  "id": 57564,
431
+ "content": "</s_19>",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
 
437
  },
438
  {
439
  "id": 57565,
440
+ "content": "<s_18>",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
 
446
  },
447
  {
448
  "id": 57566,
449
+ "content": "</s_18>",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
 
455
  },
456
  {
457
  "id": 57567,
458
+ "content": "<s_17>",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
 
464
  },
465
  {
466
  "id": 57568,
467
+ "content": "</s_17>",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
 
473
  },
474
  {
475
  "id": 57569,
476
+ "content": "<s_16>",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
 
482
  },
483
  {
484
  "id": 57570,
485
+ "content": "</s_16>",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
 
491
  },
492
  {
493
  "id": 57571,
494
+ "content": "<s_25>",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
 
500
  },
501
  {
502
  "id": 57572,
503
+ "content": "</s_25>",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
 
509
  },
510
  {
511
  "id": 57573,
512
+ "content": "<s_24>",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
 
518
  },
519
  {
520
  "id": 57574,
521
+ "content": "</s_24>",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
 
527
  },
528
  {
529
  "id": 57575,
530
+ "content": "<s_31>",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
 
536
  },
537
  {
538
  "id": 57576,
539
+ "content": "</s_31>",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
 
545
  },
546
  {
547
  "id": 57577,
548
+ "content": "<s_30>",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
 
554
  },
555
  {
556
  "id": 57578,
557
+ "content": "</s_30>",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
 
563
  },
564
  {
565
  "id": 57579,
566
+ "content": "<s_29>",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
 
572
  },
573
  {
574
  "id": 57580,
575
+ "content": "</s_29>",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
 
581
  },
582
  {
583
  "id": 57581,
584
+ "content": "<s_28>",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
 
590
  },
591
  {
592
  "id": 57582,
593
+ "content": "</s_28>",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
 
599
  },
600
  {
601
  "id": 57583,
602
+ "content": "<s_27>",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
 
608
  },
609
  {
610
  "id": 57584,
611
+ "content": "</s_27>",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
 
617
  },
618
  {
619
  "id": 57585,
620
+ "content": "<s_26>",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
 
626
  },
627
  {
628
  "id": 57586,
629
+ "content": "</s_26>",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
 
635
  },
636
  {
637
  "id": 57587,
638
+ "content": "<s_35>",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
 
644
  },
645
  {
646
  "id": 57588,
647
+ "content": "</s_35>",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
 
653
  },
654
  {
655
  "id": 57589,
656
+ "content": "<s_34>",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
 
662
  },
663
  {
664
  "id": 57590,
665
+ "content": "</s_34>",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
 
671
  },
672
  {
673
  "id": 57591,
674
+ "content": "<s_33>",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
 
680
  },
681
  {
682
  "id": 57592,
683
+ "content": "</s_33>",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
 
689
  },
690
  {
691
  "id": 57593,
692
+ "content": "<s_32>",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
 
698
  },
699
  {
700
  "id": 57594,
701
+ "content": "</s_32>",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
 
707
  },
708
  {
709
  "id": 57595,
710
+ "content": "<s_36>",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
 
716
  },
717
  {
718
  "id": 57596,
719
+ "content": "</s_36>",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
 
725
  },
726
  {
727
  "id": 57597,
728
+ "content": "<s_37>",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
 
734
  },
735
  {
736
  "id": 57598,
737
+ "content": "</s_37>",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
 
743
  },
744
  {
745
  "id": 57599,
746
+ "content": "<s_38>",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
 
752
  },
753
  {
754
  "id": 57600,
755
+ "content": "</s_38>",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
 
761
  },
762
  {
763
  "id": 57601,
764
+ "content": "<s_40>",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
 
770
  },
771
  {
772
  "id": 57602,
773
+ "content": "</s_40>",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
 
779
  },
780
  {
781
  "id": 57603,
782
+ "content": "<s_39>",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
 
788
  },
789
  {
790
  "id": 57604,
791
+ "content": "</s_39>",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
 
797
  },
798
  {
799
  "id": 57605,
800
+ "content": "<s_cord-v2>",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
 
806
  },
807
  {
808
  "id": 57606,
809
+ "content": "<s_question>",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
 
815
  },
816
  {
817
  "id": 57607,
818
+ "content": "</s_question>",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
 
824
  },
825
  {
826
  "id": 57608,
827
+ "content": "<s_answer>",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
 
833
  },
834
  {
835
  "id": 57609,
836
+ "content": "</s_answer>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ {
844
+ "id": 57610,
845
+ "content": "<s_docvqa>",
846
  "single_word": false,
847
  "lstrip": false,
848
  "rstrip": false,