TomasFAV commited on
Commit
bb8bf42
·
verified ·
1 Parent(s): fc6fb86

Upload processor

Browse files
Files changed (3) hide show
  1. processor_config.json +19 -0
  2. tokenizer.json +116 -119
  3. tokenizer_config.json +32 -1572
processor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "image_processor_type": "Pix2StructImageProcessorFast",
7
+ "is_vqa": true,
8
+ "max_patches": 2048,
9
+ "patch_size": {
10
+ "height": 16,
11
+ "width": 16
12
+ },
13
+ "size": {
14
+ "height": 2338,
15
+ "width": 1654
16
+ }
17
+ },
18
+ "processor_class": "Pix2StructProcessor"
19
+ }
tokenizer.json CHANGED
@@ -3,7 +3,7 @@
3
  "truncation": null,
4
  "padding": {
5
  "strategy": {
6
- "Fixed": 512
7
  },
8
  "direction": "Right",
9
  "pad_to_multiple_of": null,
@@ -941,7 +941,7 @@
941
  },
942
  {
943
  "id": 50344,
944
- "content": "<s_IBAN>",
945
  "single_word": false,
946
  "lstrip": false,
947
  "rstrip": false,
@@ -950,7 +950,7 @@
950
  },
951
  {
952
  "id": 50345,
953
- "content": "<s_total_price>",
954
  "single_word": false,
955
  "lstrip": false,
956
  "rstrip": false,
@@ -959,7 +959,7 @@
959
  },
960
  {
961
  "id": 50346,
962
- "content": "<s_const_symbol>",
963
  "single_word": false,
964
  "lstrip": false,
965
  "rstrip": false,
@@ -968,7 +968,7 @@
968
  },
969
  {
970
  "id": 50347,
971
- "content": "<s_total_vat>",
972
  "single_word": false,
973
  "lstrip": false,
974
  "rstrip": false,
@@ -977,7 +977,7 @@
977
  },
978
  {
979
  "id": 50348,
980
- "content": "<s_bank_account_number>",
981
  "single_word": false,
982
  "lstrip": false,
983
  "rstrip": false,
@@ -986,7 +986,7 @@
986
  },
987
  {
988
  "id": 50349,
989
- "content": "<s_supplier_register_id>",
990
  "single_word": false,
991
  "lstrip": false,
992
  "rstrip": false,
@@ -995,7 +995,7 @@
995
  },
996
  {
997
  "id": 50350,
998
- "content": "</s_due_date>",
999
  "single_word": false,
1000
  "lstrip": false,
1001
  "rstrip": false,
@@ -1004,7 +1004,7 @@
1004
  },
1005
  {
1006
  "id": 50351,
1007
- "content": "<s_supplier_tax_id>",
1008
  "single_word": false,
1009
  "lstrip": false,
1010
  "rstrip": false,
@@ -1013,7 +1013,7 @@
1013
  },
1014
  {
1015
  "id": 50352,
1016
- "content": "<s_taxable_supply_date>",
1017
  "single_word": false,
1018
  "lstrip": false,
1019
  "rstrip": false,
@@ -1022,7 +1022,7 @@
1022
  },
1023
  {
1024
  "id": 50353,
1025
- "content": "</s_payment>",
1026
  "single_word": false,
1027
  "lstrip": false,
1028
  "rstrip": false,
@@ -1031,7 +1031,7 @@
1031
  },
1032
  {
1033
  "id": 50354,
1034
- "content": "</s_total_vat>",
1035
  "single_word": false,
1036
  "lstrip": false,
1037
  "rstrip": false,
@@ -1040,7 +1040,7 @@
1040
  },
1041
  {
1042
  "id": 50355,
1043
- "content": "</s_customer_name>",
1044
  "single_word": false,
1045
  "lstrip": false,
1046
  "rstrip": false,
@@ -1049,7 +1049,7 @@
1049
  },
1050
  {
1051
  "id": 50356,
1052
- "content": "</s_taxable_supply_date>",
1053
  "single_word": false,
1054
  "lstrip": false,
1055
  "rstrip": false,
@@ -1058,7 +1058,7 @@
1058
  },
1059
  {
1060
  "id": 50357,
1061
- "content": "<s_issue_date>",
1062
  "single_word": false,
1063
  "lstrip": false,
1064
  "rstrip": false,
@@ -1067,7 +1067,7 @@
1067
  },
1068
  {
1069
  "id": 50358,
1070
- "content": "</s_bank_account_number>",
1071
  "single_word": false,
1072
  "lstrip": false,
1073
  "rstrip": false,
@@ -1076,7 +1076,7 @@
1076
  },
1077
  {
1078
  "id": 50359,
1079
- "content": "<s_supplier_name>",
1080
  "single_word": false,
1081
  "lstrip": false,
1082
  "rstrip": false,
@@ -1085,7 +1085,7 @@
1085
  },
1086
  {
1087
  "id": 50360,
1088
- "content": "<s_payment>",
1089
  "single_word": false,
1090
  "lstrip": false,
1091
  "rstrip": false,
@@ -1094,7 +1094,7 @@
1094
  },
1095
  {
1096
  "id": 50361,
1097
- "content": "</s_supplier_tax_id>",
1098
  "single_word": false,
1099
  "lstrip": false,
1100
  "rstrip": false,
@@ -1103,7 +1103,7 @@
1103
  },
1104
  {
1105
  "id": 50362,
1106
- "content": "</s_invoice_number>",
1107
  "single_word": false,
1108
  "lstrip": false,
1109
  "rstrip": false,
@@ -1112,7 +1112,7 @@
1112
  },
1113
  {
1114
  "id": 50363,
1115
- "content": "<s_due_date>",
1116
  "single_word": false,
1117
  "lstrip": false,
1118
  "rstrip": false,
@@ -1121,7 +1121,7 @@
1121
  },
1122
  {
1123
  "id": 50364,
1124
- "content": "<s_currency>",
1125
  "single_word": false,
1126
  "lstrip": false,
1127
  "rstrip": false,
@@ -1130,7 +1130,7 @@
1130
  },
1131
  {
1132
  "id": 50365,
1133
- "content": "<s_customer_register_id>",
1134
  "single_word": false,
1135
  "lstrip": false,
1136
  "rstrip": false,
@@ -1139,7 +1139,7 @@
1139
  },
1140
  {
1141
  "id": 50366,
1142
- "content": "</s_customer_register_id>",
1143
  "single_word": false,
1144
  "lstrip": false,
1145
  "rstrip": false,
@@ -1148,7 +1148,7 @@
1148
  },
1149
  {
1150
  "id": 50367,
1151
- "content": "</s_issue_date>",
1152
  "single_word": false,
1153
  "lstrip": false,
1154
  "rstrip": false,
@@ -1157,7 +1157,7 @@
1157
  },
1158
  {
1159
  "id": 50368,
1160
- "content": "</s_variable_symbol>",
1161
  "single_word": false,
1162
  "lstrip": false,
1163
  "rstrip": false,
@@ -1166,7 +1166,7 @@
1166
  },
1167
  {
1168
  "id": 50369,
1169
- "content": "</s_BIC>",
1170
  "single_word": false,
1171
  "lstrip": false,
1172
  "rstrip": false,
@@ -1175,7 +1175,7 @@
1175
  },
1176
  {
1177
  "id": 50370,
1178
- "content": "</s_customer_tax_id>",
1179
  "single_word": false,
1180
  "lstrip": false,
1181
  "rstrip": false,
@@ -1184,7 +1184,7 @@
1184
  },
1185
  {
1186
  "id": 50371,
1187
- "content": "</s_total_price>",
1188
  "single_word": false,
1189
  "lstrip": false,
1190
  "rstrip": false,
@@ -1193,7 +1193,7 @@
1193
  },
1194
  {
1195
  "id": 50372,
1196
- "content": "</s_IBAN>",
1197
  "single_word": false,
1198
  "lstrip": false,
1199
  "rstrip": false,
@@ -1202,7 +1202,7 @@
1202
  },
1203
  {
1204
  "id": 50373,
1205
- "content": "<s_customer_tax_id>",
1206
  "single_word": false,
1207
  "lstrip": false,
1208
  "rstrip": false,
@@ -1211,79 +1211,79 @@
1211
  },
1212
  {
1213
  "id": 50374,
1214
- "content": "<s_variable_symbol>",
1215
  "single_word": false,
1216
  "lstrip": false,
1217
  "rstrip": false,
1218
- "normalized": false,
1219
- "special": true
1220
  },
1221
  {
1222
  "id": 50375,
1223
- "content": "</s_supplier_register_id>",
1224
  "single_word": false,
1225
  "lstrip": false,
1226
  "rstrip": false,
1227
- "normalized": false,
1228
- "special": true
1229
  },
1230
  {
1231
  "id": 50376,
1232
- "content": "</s_currency>",
1233
  "single_word": false,
1234
  "lstrip": false,
1235
  "rstrip": false,
1236
- "normalized": false,
1237
- "special": true
1238
  },
1239
  {
1240
  "id": 50377,
1241
- "content": "<s_customer_name>",
1242
  "single_word": false,
1243
  "lstrip": false,
1244
  "rstrip": false,
1245
- "normalized": false,
1246
- "special": true
1247
  },
1248
  {
1249
  "id": 50378,
1250
- "content": "</s_supplier_name>",
1251
  "single_word": false,
1252
  "lstrip": false,
1253
  "rstrip": false,
1254
- "normalized": false,
1255
- "special": true
1256
  },
1257
  {
1258
  "id": 50379,
1259
- "content": "<s_BIC>",
1260
  "single_word": false,
1261
  "lstrip": false,
1262
  "rstrip": false,
1263
- "normalized": false,
1264
- "special": true
1265
  },
1266
  {
1267
  "id": 50380,
1268
- "content": "</s_const_symbol>",
1269
  "single_word": false,
1270
  "lstrip": false,
1271
  "rstrip": false,
1272
- "normalized": false,
1273
- "special": true
1274
  },
1275
  {
1276
  "id": 50381,
1277
- "content": "<s_invoice_number>",
1278
  "single_word": false,
1279
  "lstrip": false,
1280
  "rstrip": false,
1281
- "normalized": false,
1282
- "special": true
1283
  },
1284
  {
1285
  "id": 50382,
1286
- "content": "<reserved_1>",
1287
  "single_word": false,
1288
  "lstrip": false,
1289
  "rstrip": false,
@@ -1292,7 +1292,7 @@
1292
  },
1293
  {
1294
  "id": 50383,
1295
- "content": "<reserved_2>",
1296
  "single_word": false,
1297
  "lstrip": false,
1298
  "rstrip": false,
@@ -1301,7 +1301,7 @@
1301
  },
1302
  {
1303
  "id": 50384,
1304
- "content": "<reserved_3>",
1305
  "single_word": false,
1306
  "lstrip": false,
1307
  "rstrip": false,
@@ -1310,7 +1310,7 @@
1310
  },
1311
  {
1312
  "id": 50385,
1313
- "content": "<reserved_4>",
1314
  "single_word": false,
1315
  "lstrip": false,
1316
  "rstrip": false,
@@ -1319,7 +1319,7 @@
1319
  },
1320
  {
1321
  "id": 50386,
1322
- "content": "<reserved_5>",
1323
  "single_word": false,
1324
  "lstrip": false,
1325
  "rstrip": false,
@@ -1328,7 +1328,7 @@
1328
  },
1329
  {
1330
  "id": 50387,
1331
- "content": "<reserved_6>",
1332
  "single_word": false,
1333
  "lstrip": false,
1334
  "rstrip": false,
@@ -1337,7 +1337,7 @@
1337
  },
1338
  {
1339
  "id": 50388,
1340
- "content": "<reserved_7>",
1341
  "single_word": false,
1342
  "lstrip": false,
1343
  "rstrip": false,
@@ -1346,7 +1346,7 @@
1346
  },
1347
  {
1348
  "id": 50389,
1349
- "content": "<reserved_8>",
1350
  "single_word": false,
1351
  "lstrip": false,
1352
  "rstrip": false,
@@ -1355,7 +1355,7 @@
1355
  },
1356
  {
1357
  "id": 50390,
1358
- "content": "<reserved_9>",
1359
  "single_word": false,
1360
  "lstrip": false,
1361
  "rstrip": false,
@@ -1364,7 +1364,7 @@
1364
  },
1365
  {
1366
  "id": 50391,
1367
- "content": "<reserved_10>",
1368
  "single_word": false,
1369
  "lstrip": false,
1370
  "rstrip": false,
@@ -1373,7 +1373,7 @@
1373
  },
1374
  {
1375
  "id": 50392,
1376
- "content": "<reserved_11>",
1377
  "single_word": false,
1378
  "lstrip": false,
1379
  "rstrip": false,
@@ -1382,7 +1382,7 @@
1382
  },
1383
  {
1384
  "id": 50393,
1385
- "content": "<reserved_12>",
1386
  "single_word": false,
1387
  "lstrip": false,
1388
  "rstrip": false,
@@ -1391,7 +1391,7 @@
1391
  },
1392
  {
1393
  "id": 50394,
1394
- "content": "<reserved_13>",
1395
  "single_word": false,
1396
  "lstrip": false,
1397
  "rstrip": false,
@@ -1400,7 +1400,7 @@
1400
  },
1401
  {
1402
  "id": 50395,
1403
- "content": "<reserved_14>",
1404
  "single_word": false,
1405
  "lstrip": false,
1406
  "rstrip": false,
@@ -1409,7 +1409,7 @@
1409
  },
1410
  {
1411
  "id": 50396,
1412
- "content": "<reserved_15>",
1413
  "single_word": false,
1414
  "lstrip": false,
1415
  "rstrip": false,
@@ -1418,7 +1418,7 @@
1418
  },
1419
  {
1420
  "id": 50397,
1421
- "content": "<reserved_16>",
1422
  "single_word": false,
1423
  "lstrip": false,
1424
  "rstrip": false,
@@ -1427,7 +1427,7 @@
1427
  },
1428
  {
1429
  "id": 50398,
1430
- "content": "<reserved_17>",
1431
  "single_word": false,
1432
  "lstrip": false,
1433
  "rstrip": false,
@@ -1436,7 +1436,7 @@
1436
  },
1437
  {
1438
  "id": 50399,
1439
- "content": "<reserved_18>",
1440
  "single_word": false,
1441
  "lstrip": false,
1442
  "rstrip": false,
@@ -1445,7 +1445,7 @@
1445
  },
1446
  {
1447
  "id": 50400,
1448
- "content": "<reserved_19>",
1449
  "single_word": false,
1450
  "lstrip": false,
1451
  "rstrip": false,
@@ -1454,7 +1454,7 @@
1454
  },
1455
  {
1456
  "id": 50401,
1457
- "content": "<reserved_20>",
1458
  "single_word": false,
1459
  "lstrip": false,
1460
  "rstrip": false,
@@ -1463,7 +1463,7 @@
1463
  },
1464
  {
1465
  "id": 50402,
1466
- "content": "<reserved_21>",
1467
  "single_word": false,
1468
  "lstrip": false,
1469
  "rstrip": false,
@@ -1472,7 +1472,7 @@
1472
  },
1473
  {
1474
  "id": 50403,
1475
- "content": "<reserved_22>",
1476
  "single_word": false,
1477
  "lstrip": false,
1478
  "rstrip": false,
@@ -1481,7 +1481,7 @@
1481
  },
1482
  {
1483
  "id": 50404,
1484
- "content": "<reserved_23>",
1485
  "single_word": false,
1486
  "lstrip": false,
1487
  "rstrip": false,
@@ -1490,7 +1490,7 @@
1490
  },
1491
  {
1492
  "id": 50405,
1493
- "content": "<reserved_24>",
1494
  "single_word": false,
1495
  "lstrip": false,
1496
  "rstrip": false,
@@ -1499,7 +1499,7 @@
1499
  },
1500
  {
1501
  "id": 50406,
1502
- "content": "<reserved_25>",
1503
  "single_word": false,
1504
  "lstrip": false,
1505
  "rstrip": false,
@@ -1508,7 +1508,7 @@
1508
  },
1509
  {
1510
  "id": 50407,
1511
- "content": "<reserved_26>",
1512
  "single_word": false,
1513
  "lstrip": false,
1514
  "rstrip": false,
@@ -1517,7 +1517,7 @@
1517
  },
1518
  {
1519
  "id": 50408,
1520
- "content": "<reserved_27>",
1521
  "single_word": false,
1522
  "lstrip": false,
1523
  "rstrip": false,
@@ -1526,7 +1526,7 @@
1526
  },
1527
  {
1528
  "id": 50409,
1529
- "content": "<reserved_28>",
1530
  "single_word": false,
1531
  "lstrip": false,
1532
  "rstrip": false,
@@ -1535,7 +1535,7 @@
1535
  },
1536
  {
1537
  "id": 50410,
1538
- "content": "<reserved_29>",
1539
  "single_word": false,
1540
  "lstrip": false,
1541
  "rstrip": false,
@@ -1544,7 +1544,7 @@
1544
  },
1545
  {
1546
  "id": 50411,
1547
- "content": "<reserved_30>",
1548
  "single_word": false,
1549
  "lstrip": false,
1550
  "rstrip": false,
@@ -1553,7 +1553,7 @@
1553
  },
1554
  {
1555
  "id": 50412,
1556
- "content": "<reserved_31>",
1557
  "single_word": false,
1558
  "lstrip": false,
1559
  "rstrip": false,
@@ -1562,7 +1562,7 @@
1562
  },
1563
  {
1564
  "id": 50413,
1565
- "content": "<reserved_32>",
1566
  "single_word": false,
1567
  "lstrip": false,
1568
  "rstrip": false,
@@ -1571,7 +1571,7 @@
1571
  },
1572
  {
1573
  "id": 50414,
1574
- "content": "<reserved_33>",
1575
  "single_word": false,
1576
  "lstrip": false,
1577
  "rstrip": false,
@@ -1580,7 +1580,7 @@
1580
  },
1581
  {
1582
  "id": 50415,
1583
- "content": "<reserved_34>",
1584
  "single_word": false,
1585
  "lstrip": false,
1586
  "rstrip": false,
@@ -1589,7 +1589,7 @@
1589
  },
1590
  {
1591
  "id": 50416,
1592
- "content": "<reserved_35>",
1593
  "single_word": false,
1594
  "lstrip": false,
1595
  "rstrip": false,
@@ -1598,7 +1598,7 @@
1598
  },
1599
  {
1600
  "id": 50417,
1601
- "content": "<reserved_36>",
1602
  "single_word": false,
1603
  "lstrip": false,
1604
  "rstrip": false,
@@ -1607,7 +1607,7 @@
1607
  },
1608
  {
1609
  "id": 50418,
1610
- "content": "<reserved_37>",
1611
  "single_word": false,
1612
  "lstrip": false,
1613
  "rstrip": false,
@@ -1616,7 +1616,7 @@
1616
  },
1617
  {
1618
  "id": 50419,
1619
- "content": "<reserved_38>",
1620
  "single_word": false,
1621
  "lstrip": false,
1622
  "rstrip": false,
@@ -1625,7 +1625,7 @@
1625
  },
1626
  {
1627
  "id": 50420,
1628
- "content": "<reserved_39>",
1629
  "single_word": false,
1630
  "lstrip": false,
1631
  "rstrip": false,
@@ -1634,7 +1634,7 @@
1634
  },
1635
  {
1636
  "id": 50421,
1637
- "content": "<reserved_40>",
1638
  "single_word": false,
1639
  "lstrip": false,
1640
  "rstrip": false,
@@ -1643,7 +1643,7 @@
1643
  },
1644
  {
1645
  "id": 50422,
1646
- "content": "<reserved_41>",
1647
  "single_word": false,
1648
  "lstrip": false,
1649
  "rstrip": false,
@@ -1652,7 +1652,7 @@
1652
  },
1653
  {
1654
  "id": 50423,
1655
- "content": "<reserved_42>",
1656
  "single_word": false,
1657
  "lstrip": false,
1658
  "rstrip": false,
@@ -1661,7 +1661,7 @@
1661
  },
1662
  {
1663
  "id": 50424,
1664
- "content": "<reserved_43>",
1665
  "single_word": false,
1666
  "lstrip": false,
1667
  "rstrip": false,
@@ -1670,7 +1670,7 @@
1670
  },
1671
  {
1672
  "id": 50425,
1673
- "content": "<reserved_44>",
1674
  "single_word": false,
1675
  "lstrip": false,
1676
  "rstrip": false,
@@ -1679,7 +1679,7 @@
1679
  },
1680
  {
1681
  "id": 50426,
1682
- "content": "<reserved_45>",
1683
  "single_word": false,
1684
  "lstrip": false,
1685
  "rstrip": false,
@@ -1688,7 +1688,7 @@
1688
  },
1689
  {
1690
  "id": 50427,
1691
- "content": "<reserved_46>",
1692
  "single_word": false,
1693
  "lstrip": false,
1694
  "rstrip": false,
@@ -1697,7 +1697,7 @@
1697
  },
1698
  {
1699
  "id": 50428,
1700
- "content": "<reserved_47>",
1701
  "single_word": false,
1702
  "lstrip": false,
1703
  "rstrip": false,
@@ -1706,7 +1706,7 @@
1706
  },
1707
  {
1708
  "id": 50429,
1709
- "content": "<reserved_48>",
1710
  "single_word": false,
1711
  "lstrip": false,
1712
  "rstrip": false,
@@ -1715,7 +1715,7 @@
1715
  },
1716
  {
1717
  "id": 50430,
1718
- "content": "<reserved_49>",
1719
  "single_word": false,
1720
  "lstrip": false,
1721
  "rstrip": false,
@@ -1724,7 +1724,7 @@
1724
  },
1725
  {
1726
  "id": 50431,
1727
- "content": "<reserved_50>",
1728
  "single_word": false,
1729
  "lstrip": false,
1730
  "rstrip": false,
@@ -1732,24 +1732,21 @@
1732
  "special": false
1733
  }
1734
  ],
1735
- "normalizer": {
 
1736
  "type": "Sequence",
1737
- "normalizers": [
1738
  {
1739
- "type": "Replace",
1740
- "pattern": {
1741
- "Regex": " {2,}"
1742
- },
1743
- "content": " "
 
 
1744
  }
1745
  ]
1746
  },
1747
- "pre_tokenizer": {
1748
- "type": "Metaspace",
1749
- "replacement": "▁",
1750
- "prepend_scheme": "always",
1751
- "split": true
1752
- },
1753
  "post_processor": {
1754
  "type": "TemplateProcessing",
1755
  "single": [
@@ -1812,7 +1809,7 @@
1812
  },
1813
  "model": {
1814
  "type": "Unigram",
1815
- "unk_id": 3,
1816
  "vocab": [
1817
  [
1818
  "<pad>",
 
3
  "truncation": null,
4
  "padding": {
5
  "strategy": {
6
+ "Fixed": 768
7
  },
8
  "direction": "Right",
9
  "pad_to_multiple_of": null,
 
941
  },
942
  {
943
  "id": 50344,
944
+ "content": "</s_supp_tax_id>",
945
  "single_word": false,
946
  "lstrip": false,
947
  "rstrip": false,
 
950
  },
951
  {
952
  "id": 50345,
953
+ "content": "<s_issue_date>",
954
  "single_word": false,
955
  "lstrip": false,
956
  "rstrip": false,
 
959
  },
960
  {
961
  "id": 50346,
962
+ "content": "</s_bic>",
963
  "single_word": false,
964
  "lstrip": false,
965
  "rstrip": false,
 
968
  },
969
  {
970
  "id": 50347,
971
+ "content": "<s_supp_tax_id>",
972
  "single_word": false,
973
  "lstrip": false,
974
  "rstrip": false,
 
977
  },
978
  {
979
  "id": 50348,
980
+ "content": "</s_invoice_number>",
981
  "single_word": false,
982
  "lstrip": false,
983
  "rstrip": false,
 
986
  },
987
  {
988
  "id": 50349,
989
+ "content": "</s_const_symbol>",
990
  "single_word": false,
991
  "lstrip": false,
992
  "rstrip": false,
 
995
  },
996
  {
997
  "id": 50350,
998
+ "content": "<s_cust_register_id>",
999
  "single_word": false,
1000
  "lstrip": false,
1001
  "rstrip": false,
 
1004
  },
1005
  {
1006
  "id": 50351,
1007
+ "content": "</s_cust_register_id>",
1008
  "single_word": false,
1009
  "lstrip": false,
1010
  "rstrip": false,
 
1013
  },
1014
  {
1015
  "id": 50352,
1016
+ "content": "</s_taxable_supply_date>",
1017
  "single_word": false,
1018
  "lstrip": false,
1019
  "rstrip": false,
 
1022
  },
1023
  {
1024
  "id": 50353,
1025
+ "content": "<s_cust_tax_id>",
1026
  "single_word": false,
1027
  "lstrip": false,
1028
  "rstrip": false,
 
1031
  },
1032
  {
1033
  "id": 50354,
1034
+ "content": "</s_variable_symbol>",
1035
  "single_word": false,
1036
  "lstrip": false,
1037
  "rstrip": false,
 
1040
  },
1041
  {
1042
  "id": 50355,
1043
+ "content": "</s_issue_date>",
1044
  "single_word": false,
1045
  "lstrip": false,
1046
  "rstrip": false,
 
1049
  },
1050
  {
1051
  "id": 50356,
1052
+ "content": "</s_cust_tax_id>",
1053
  "single_word": false,
1054
  "lstrip": false,
1055
  "rstrip": false,
 
1058
  },
1059
  {
1060
  "id": 50357,
1061
+ "content": "<s_invoice_number>",
1062
  "single_word": false,
1063
  "lstrip": false,
1064
  "rstrip": false,
 
1067
  },
1068
  {
1069
  "id": 50358,
1070
+ "content": "<s_taxable_supply_date>",
1071
  "single_word": false,
1072
  "lstrip": false,
1073
  "rstrip": false,
 
1076
  },
1077
  {
1078
  "id": 50359,
1079
+ "content": "<s_supp_register_id>",
1080
  "single_word": false,
1081
  "lstrip": false,
1082
  "rstrip": false,
 
1085
  },
1086
  {
1087
  "id": 50360,
1088
+ "content": "<s_payment_type>",
1089
  "single_word": false,
1090
  "lstrip": false,
1091
  "rstrip": false,
 
1094
  },
1095
  {
1096
  "id": 50361,
1097
+ "content": "<s_bic>",
1098
  "single_word": false,
1099
  "lstrip": false,
1100
  "rstrip": false,
 
1103
  },
1104
  {
1105
  "id": 50362,
1106
+ "content": "</s_bank_account_number>",
1107
  "single_word": false,
1108
  "lstrip": false,
1109
  "rstrip": false,
 
1112
  },
1113
  {
1114
  "id": 50363,
1115
+ "content": "</s_total>",
1116
  "single_word": false,
1117
  "lstrip": false,
1118
  "rstrip": false,
 
1121
  },
1122
  {
1123
  "id": 50364,
1124
+ "content": "</s_payment_type>",
1125
  "single_word": false,
1126
  "lstrip": false,
1127
  "rstrip": false,
 
1130
  },
1131
  {
1132
  "id": 50365,
1133
+ "content": "<s_bank_account_number>",
1134
  "single_word": false,
1135
  "lstrip": false,
1136
  "rstrip": false,
 
1139
  },
1140
  {
1141
  "id": 50366,
1142
+ "content": "<s_iban>",
1143
  "single_word": false,
1144
  "lstrip": false,
1145
  "rstrip": false,
 
1148
  },
1149
  {
1150
  "id": 50367,
1151
+ "content": "</s_iban>",
1152
  "single_word": false,
1153
  "lstrip": false,
1154
  "rstrip": false,
 
1157
  },
1158
  {
1159
  "id": 50368,
1160
+ "content": "</s_supp_register_id>",
1161
  "single_word": false,
1162
  "lstrip": false,
1163
  "rstrip": false,
 
1166
  },
1167
  {
1168
  "id": 50369,
1169
+ "content": "<s_const_symbol>",
1170
  "single_word": false,
1171
  "lstrip": false,
1172
  "rstrip": false,
 
1175
  },
1176
  {
1177
  "id": 50370,
1178
+ "content": "<s_total>",
1179
  "single_word": false,
1180
  "lstrip": false,
1181
  "rstrip": false,
 
1184
  },
1185
  {
1186
  "id": 50371,
1187
+ "content": "<s_variable_symbol>",
1188
  "single_word": false,
1189
  "lstrip": false,
1190
  "rstrip": false,
 
1193
  },
1194
  {
1195
  "id": 50372,
1196
+ "content": "</s_due_date>",
1197
  "single_word": false,
1198
  "lstrip": false,
1199
  "rstrip": false,
 
1202
  },
1203
  {
1204
  "id": 50373,
1205
+ "content": "<s_due_date>",
1206
  "single_word": false,
1207
  "lstrip": false,
1208
  "rstrip": false,
 
1211
  },
1212
  {
1213
  "id": 50374,
1214
+ "content": "<reserved_1>",
1215
  "single_word": false,
1216
  "lstrip": false,
1217
  "rstrip": false,
1218
+ "normalized": true,
1219
+ "special": false
1220
  },
1221
  {
1222
  "id": 50375,
1223
+ "content": "<reserved_2>",
1224
  "single_word": false,
1225
  "lstrip": false,
1226
  "rstrip": false,
1227
+ "normalized": true,
1228
+ "special": false
1229
  },
1230
  {
1231
  "id": 50376,
1232
+ "content": "<reserved_3>",
1233
  "single_word": false,
1234
  "lstrip": false,
1235
  "rstrip": false,
1236
+ "normalized": true,
1237
+ "special": false
1238
  },
1239
  {
1240
  "id": 50377,
1241
+ "content": "<reserved_4>",
1242
  "single_word": false,
1243
  "lstrip": false,
1244
  "rstrip": false,
1245
+ "normalized": true,
1246
+ "special": false
1247
  },
1248
  {
1249
  "id": 50378,
1250
+ "content": "<reserved_5>",
1251
  "single_word": false,
1252
  "lstrip": false,
1253
  "rstrip": false,
1254
+ "normalized": true,
1255
+ "special": false
1256
  },
1257
  {
1258
  "id": 50379,
1259
+ "content": "<reserved_6>",
1260
  "single_word": false,
1261
  "lstrip": false,
1262
  "rstrip": false,
1263
+ "normalized": true,
1264
+ "special": false
1265
  },
1266
  {
1267
  "id": 50380,
1268
+ "content": "<reserved_7>",
1269
  "single_word": false,
1270
  "lstrip": false,
1271
  "rstrip": false,
1272
+ "normalized": true,
1273
+ "special": false
1274
  },
1275
  {
1276
  "id": 50381,
1277
+ "content": "<reserved_8>",
1278
  "single_word": false,
1279
  "lstrip": false,
1280
  "rstrip": false,
1281
+ "normalized": true,
1282
+ "special": false
1283
  },
1284
  {
1285
  "id": 50382,
1286
+ "content": "<reserved_9>",
1287
  "single_word": false,
1288
  "lstrip": false,
1289
  "rstrip": false,
 
1292
  },
1293
  {
1294
  "id": 50383,
1295
+ "content": "<reserved_10>",
1296
  "single_word": false,
1297
  "lstrip": false,
1298
  "rstrip": false,
 
1301
  },
1302
  {
1303
  "id": 50384,
1304
+ "content": "<reserved_11>",
1305
  "single_word": false,
1306
  "lstrip": false,
1307
  "rstrip": false,
 
1310
  },
1311
  {
1312
  "id": 50385,
1313
+ "content": "<reserved_12>",
1314
  "single_word": false,
1315
  "lstrip": false,
1316
  "rstrip": false,
 
1319
  },
1320
  {
1321
  "id": 50386,
1322
+ "content": "<reserved_13>",
1323
  "single_word": false,
1324
  "lstrip": false,
1325
  "rstrip": false,
 
1328
  },
1329
  {
1330
  "id": 50387,
1331
+ "content": "<reserved_14>",
1332
  "single_word": false,
1333
  "lstrip": false,
1334
  "rstrip": false,
 
1337
  },
1338
  {
1339
  "id": 50388,
1340
+ "content": "<reserved_15>",
1341
  "single_word": false,
1342
  "lstrip": false,
1343
  "rstrip": false,
 
1346
  },
1347
  {
1348
  "id": 50389,
1349
+ "content": "<reserved_16>",
1350
  "single_word": false,
1351
  "lstrip": false,
1352
  "rstrip": false,
 
1355
  },
1356
  {
1357
  "id": 50390,
1358
+ "content": "<reserved_17>",
1359
  "single_word": false,
1360
  "lstrip": false,
1361
  "rstrip": false,
 
1364
  },
1365
  {
1366
  "id": 50391,
1367
+ "content": "<reserved_18>",
1368
  "single_word": false,
1369
  "lstrip": false,
1370
  "rstrip": false,
 
1373
  },
1374
  {
1375
  "id": 50392,
1376
+ "content": "<reserved_19>",
1377
  "single_word": false,
1378
  "lstrip": false,
1379
  "rstrip": false,
 
1382
  },
1383
  {
1384
  "id": 50393,
1385
+ "content": "<reserved_20>",
1386
  "single_word": false,
1387
  "lstrip": false,
1388
  "rstrip": false,
 
1391
  },
1392
  {
1393
  "id": 50394,
1394
+ "content": "<reserved_21>",
1395
  "single_word": false,
1396
  "lstrip": false,
1397
  "rstrip": false,
 
1400
  },
1401
  {
1402
  "id": 50395,
1403
+ "content": "<reserved_22>",
1404
  "single_word": false,
1405
  "lstrip": false,
1406
  "rstrip": false,
 
1409
  },
1410
  {
1411
  "id": 50396,
1412
+ "content": "<reserved_23>",
1413
  "single_word": false,
1414
  "lstrip": false,
1415
  "rstrip": false,
 
1418
  },
1419
  {
1420
  "id": 50397,
1421
+ "content": "<reserved_24>",
1422
  "single_word": false,
1423
  "lstrip": false,
1424
  "rstrip": false,
 
1427
  },
1428
  {
1429
  "id": 50398,
1430
+ "content": "<reserved_25>",
1431
  "single_word": false,
1432
  "lstrip": false,
1433
  "rstrip": false,
 
1436
  },
1437
  {
1438
  "id": 50399,
1439
+ "content": "<reserved_26>",
1440
  "single_word": false,
1441
  "lstrip": false,
1442
  "rstrip": false,
 
1445
  },
1446
  {
1447
  "id": 50400,
1448
+ "content": "<reserved_27>",
1449
  "single_word": false,
1450
  "lstrip": false,
1451
  "rstrip": false,
 
1454
  },
1455
  {
1456
  "id": 50401,
1457
+ "content": "<reserved_28>",
1458
  "single_word": false,
1459
  "lstrip": false,
1460
  "rstrip": false,
 
1463
  },
1464
  {
1465
  "id": 50402,
1466
+ "content": "<reserved_29>",
1467
  "single_word": false,
1468
  "lstrip": false,
1469
  "rstrip": false,
 
1472
  },
1473
  {
1474
  "id": 50403,
1475
+ "content": "<reserved_30>",
1476
  "single_word": false,
1477
  "lstrip": false,
1478
  "rstrip": false,
 
1481
  },
1482
  {
1483
  "id": 50404,
1484
+ "content": "<reserved_31>",
1485
  "single_word": false,
1486
  "lstrip": false,
1487
  "rstrip": false,
 
1490
  },
1491
  {
1492
  "id": 50405,
1493
+ "content": "<reserved_32>",
1494
  "single_word": false,
1495
  "lstrip": false,
1496
  "rstrip": false,
 
1499
  },
1500
  {
1501
  "id": 50406,
1502
+ "content": "<reserved_33>",
1503
  "single_word": false,
1504
  "lstrip": false,
1505
  "rstrip": false,
 
1508
  },
1509
  {
1510
  "id": 50407,
1511
+ "content": "<reserved_34>",
1512
  "single_word": false,
1513
  "lstrip": false,
1514
  "rstrip": false,
 
1517
  },
1518
  {
1519
  "id": 50408,
1520
+ "content": "<reserved_35>",
1521
  "single_word": false,
1522
  "lstrip": false,
1523
  "rstrip": false,
 
1526
  },
1527
  {
1528
  "id": 50409,
1529
+ "content": "<reserved_36>",
1530
  "single_word": false,
1531
  "lstrip": false,
1532
  "rstrip": false,
 
1535
  },
1536
  {
1537
  "id": 50410,
1538
+ "content": "<reserved_37>",
1539
  "single_word": false,
1540
  "lstrip": false,
1541
  "rstrip": false,
 
1544
  },
1545
  {
1546
  "id": 50411,
1547
+ "content": "<reserved_38>",
1548
  "single_word": false,
1549
  "lstrip": false,
1550
  "rstrip": false,
 
1553
  },
1554
  {
1555
  "id": 50412,
1556
+ "content": "<reserved_39>",
1557
  "single_word": false,
1558
  "lstrip": false,
1559
  "rstrip": false,
 
1562
  },
1563
  {
1564
  "id": 50413,
1565
+ "content": "<reserved_40>",
1566
  "single_word": false,
1567
  "lstrip": false,
1568
  "rstrip": false,
 
1571
  },
1572
  {
1573
  "id": 50414,
1574
+ "content": "<reserved_41>",
1575
  "single_word": false,
1576
  "lstrip": false,
1577
  "rstrip": false,
 
1580
  },
1581
  {
1582
  "id": 50415,
1583
+ "content": "<reserved_42>",
1584
  "single_word": false,
1585
  "lstrip": false,
1586
  "rstrip": false,
 
1589
  },
1590
  {
1591
  "id": 50416,
1592
+ "content": "<reserved_43>",
1593
  "single_word": false,
1594
  "lstrip": false,
1595
  "rstrip": false,
 
1598
  },
1599
  {
1600
  "id": 50417,
1601
+ "content": "<reserved_44>",
1602
  "single_word": false,
1603
  "lstrip": false,
1604
  "rstrip": false,
 
1607
  },
1608
  {
1609
  "id": 50418,
1610
+ "content": "<reserved_45>",
1611
  "single_word": false,
1612
  "lstrip": false,
1613
  "rstrip": false,
 
1616
  },
1617
  {
1618
  "id": 50419,
1619
+ "content": "<reserved_46>",
1620
  "single_word": false,
1621
  "lstrip": false,
1622
  "rstrip": false,
 
1625
  },
1626
  {
1627
  "id": 50420,
1628
+ "content": "<reserved_47>",
1629
  "single_word": false,
1630
  "lstrip": false,
1631
  "rstrip": false,
 
1634
  },
1635
  {
1636
  "id": 50421,
1637
+ "content": "<reserved_48>",
1638
  "single_word": false,
1639
  "lstrip": false,
1640
  "rstrip": false,
 
1643
  },
1644
  {
1645
  "id": 50422,
1646
+ "content": "<reserved_49>",
1647
  "single_word": false,
1648
  "lstrip": false,
1649
  "rstrip": false,
 
1652
  },
1653
  {
1654
  "id": 50423,
1655
+ "content": "<reserved_50>",
1656
  "single_word": false,
1657
  "lstrip": false,
1658
  "rstrip": false,
 
1661
  },
1662
  {
1663
  "id": 50424,
1664
+ "content": "<reserved_51>",
1665
  "single_word": false,
1666
  "lstrip": false,
1667
  "rstrip": false,
 
1670
  },
1671
  {
1672
  "id": 50425,
1673
+ "content": "<reserved_52>",
1674
  "single_word": false,
1675
  "lstrip": false,
1676
  "rstrip": false,
 
1679
  },
1680
  {
1681
  "id": 50426,
1682
+ "content": "<reserved_53>",
1683
  "single_word": false,
1684
  "lstrip": false,
1685
  "rstrip": false,
 
1688
  },
1689
  {
1690
  "id": 50427,
1691
+ "content": "<reserved_54>",
1692
  "single_word": false,
1693
  "lstrip": false,
1694
  "rstrip": false,
 
1697
  },
1698
  {
1699
  "id": 50428,
1700
+ "content": "<reserved_55>",
1701
  "single_word": false,
1702
  "lstrip": false,
1703
  "rstrip": false,
 
1706
  },
1707
  {
1708
  "id": 50429,
1709
+ "content": "<reserved_56>",
1710
  "single_word": false,
1711
  "lstrip": false,
1712
  "rstrip": false,
 
1715
  },
1716
  {
1717
  "id": 50430,
1718
+ "content": "<reserved_57>",
1719
  "single_word": false,
1720
  "lstrip": false,
1721
  "rstrip": false,
 
1724
  },
1725
  {
1726
  "id": 50431,
1727
+ "content": "<reserved_58>",
1728
  "single_word": false,
1729
  "lstrip": false,
1730
  "rstrip": false,
 
1732
  "special": false
1733
  }
1734
  ],
1735
+ "normalizer": null,
1736
+ "pre_tokenizer": {
1737
  "type": "Sequence",
1738
+ "pretokenizers": [
1739
  {
1740
+ "type": "WhitespaceSplit"
1741
+ },
1742
+ {
1743
+ "type": "Metaspace",
1744
+ "replacement": "",
1745
+ "prepend_scheme": "always",
1746
+ "split": true
1747
  }
1748
  ]
1749
  },
 
 
 
 
 
 
1750
  "post_processor": {
1751
  "type": "TemplateProcessing",
1752
  "single": [
 
1809
  },
1810
  "model": {
1811
  "type": "Unigram",
1812
+ "unk_id": 2,
1813
  "vocab": [
1814
  [
1815
  "<pad>",
tokenizer_config.json CHANGED
@@ -1,1585 +1,45 @@
1
  {
2
- "add_prefix_space": null,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "3": {
21
- "content": "<unk>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "50244": {
29
- "content": "<extra_id_99>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50245": {
37
- "content": "<extra_id_98>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "50246": {
45
- "content": "<extra_id_97>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "50247": {
53
- "content": "<extra_id_96>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "50248": {
61
- "content": "<extra_id_95>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "50249": {
69
- "content": "<extra_id_94>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "50250": {
77
- "content": "<extra_id_93>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "50251": {
85
- "content": "<extra_id_92>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "50252": {
93
- "content": "<extra_id_91>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "50253": {
101
- "content": "<extra_id_90>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "50254": {
109
- "content": "<extra_id_89>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "50255": {
117
- "content": "<extra_id_88>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "50256": {
125
- "content": "<extra_id_87>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "50257": {
133
- "content": "<extra_id_86>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "50258": {
141
- "content": "<extra_id_85>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "50259": {
149
- "content": "<extra_id_84>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "50260": {
157
- "content": "<extra_id_83>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "50261": {
165
- "content": "<extra_id_82>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "50262": {
173
- "content": "<extra_id_81>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "50263": {
181
- "content": "<extra_id_80>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "50264": {
189
- "content": "<extra_id_79>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "50265": {
197
- "content": "<extra_id_78>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "50266": {
205
- "content": "<extra_id_77>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "50267": {
213
- "content": "<extra_id_76>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "50268": {
221
- "content": "<extra_id_75>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "50269": {
229
- "content": "<extra_id_74>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "50270": {
237
- "content": "<extra_id_73>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "50271": {
245
- "content": "<extra_id_72>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "50272": {
253
- "content": "<extra_id_71>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "50273": {
261
- "content": "<extra_id_70>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "50274": {
269
- "content": "<extra_id_69>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "50275": {
277
- "content": "<extra_id_68>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "50276": {
285
- "content": "<extra_id_67>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "50277": {
293
- "content": "<extra_id_66>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "50278": {
301
- "content": "<extra_id_65>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "50279": {
309
- "content": "<extra_id_64>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "50280": {
317
- "content": "<extra_id_63>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "50281": {
325
- "content": "<extra_id_62>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "50282": {
333
- "content": "<extra_id_61>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "50283": {
341
- "content": "<extra_id_60>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "50284": {
349
- "content": "<extra_id_59>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "50285": {
357
- "content": "<extra_id_58>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "50286": {
365
- "content": "<extra_id_57>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "50287": {
373
- "content": "<extra_id_56>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "50288": {
381
- "content": "<extra_id_55>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "50289": {
389
- "content": "<extra_id_54>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "50290": {
397
- "content": "<extra_id_53>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "50291": {
405
- "content": "<extra_id_52>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "50292": {
413
- "content": "<extra_id_51>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "50293": {
421
- "content": "<extra_id_50>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "50294": {
429
- "content": "<extra_id_49>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "50295": {
437
- "content": "<extra_id_48>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "50296": {
445
- "content": "<extra_id_47>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "50297": {
453
- "content": "<extra_id_46>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "50298": {
461
- "content": "<extra_id_45>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "50299": {
469
- "content": "<extra_id_44>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "50300": {
477
- "content": "<extra_id_43>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "50301": {
485
- "content": "<extra_id_42>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "50302": {
493
- "content": "<extra_id_41>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "50303": {
501
- "content": "<extra_id_40>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "50304": {
509
- "content": "<extra_id_39>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "50305": {
517
- "content": "<extra_id_38>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "50306": {
525
- "content": "<extra_id_37>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "50307": {
533
- "content": "<extra_id_36>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "50308": {
541
- "content": "<extra_id_35>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "50309": {
549
- "content": "<extra_id_34>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "50310": {
557
- "content": "<extra_id_33>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "50311": {
565
- "content": "<extra_id_32>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "50312": {
573
- "content": "<extra_id_31>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "50313": {
581
- "content": "<extra_id_30>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "50314": {
589
- "content": "<extra_id_29>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "50315": {
597
- "content": "<extra_id_28>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "50316": {
605
- "content": "<extra_id_27>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "50317": {
613
- "content": "<extra_id_26>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "50318": {
621
- "content": "<extra_id_25>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": true
627
- },
628
- "50319": {
629
- "content": "<extra_id_24>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": true
635
- },
636
- "50320": {
637
- "content": "<extra_id_23>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": true
643
- },
644
- "50321": {
645
- "content": "<extra_id_22>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": true
651
- },
652
- "50322": {
653
- "content": "<extra_id_21>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": true
659
- },
660
- "50323": {
661
- "content": "<extra_id_20>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": true
667
- },
668
- "50324": {
669
- "content": "<extra_id_19>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": true
675
- },
676
- "50325": {
677
- "content": "<extra_id_18>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": true
683
- },
684
- "50326": {
685
- "content": "<extra_id_17>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": true
691
- },
692
- "50327": {
693
- "content": "<extra_id_16>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": true
699
- },
700
- "50328": {
701
- "content": "<extra_id_15>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": true
707
- },
708
- "50329": {
709
- "content": "<extra_id_14>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": true
715
- },
716
- "50330": {
717
- "content": "<extra_id_13>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": true
723
- },
724
- "50331": {
725
- "content": "<extra_id_12>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": true
731
- },
732
- "50332": {
733
- "content": "<extra_id_11>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": true
739
- },
740
- "50333": {
741
- "content": "<extra_id_10>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": true
747
- },
748
- "50334": {
749
- "content": "<extra_id_9>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": true
755
- },
756
- "50335": {
757
- "content": "<extra_id_8>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": true
763
- },
764
- "50336": {
765
- "content": "<extra_id_7>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": true
771
- },
772
- "50337": {
773
- "content": "<extra_id_6>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": true
779
- },
780
- "50338": {
781
- "content": "<extra_id_5>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": true
787
- },
788
- "50339": {
789
- "content": "<extra_id_4>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": true
795
- },
796
- "50340": {
797
- "content": "<extra_id_3>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": true
803
- },
804
- "50341": {
805
- "content": "<extra_id_2>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": true
811
- },
812
- "50342": {
813
- "content": "<extra_id_1>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": true
819
- },
820
- "50343": {
821
- "content": "<extra_id_0>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": true
827
- },
828
- "50344": {
829
- "content": "<s_IBAN>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": true
835
- },
836
- "50345": {
837
- "content": "<s_total_price>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": true
843
- },
844
- "50346": {
845
- "content": "<s_const_symbol>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": true
851
- },
852
- "50347": {
853
- "content": "<s_total_vat>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "50348": {
861
- "content": "<s_bank_account_number>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "50349": {
869
- "content": "<s_supplier_register_id>",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": true
875
- },
876
- "50350": {
877
- "content": "</s_due_date>",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": true
883
- },
884
- "50351": {
885
- "content": "<s_supplier_tax_id>",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": true
891
- },
892
- "50352": {
893
- "content": "<s_taxable_supply_date>",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": true
899
- },
900
- "50353": {
901
- "content": "</s_payment>",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": true
907
- },
908
- "50354": {
909
- "content": "</s_total_vat>",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": true
915
- },
916
- "50355": {
917
- "content": "</s_customer_name>",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": true
923
- },
924
- "50356": {
925
- "content": "</s_taxable_supply_date>",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": true
931
- },
932
- "50357": {
933
- "content": "<s_issue_date>",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": true
939
- },
940
- "50358": {
941
- "content": "</s_bank_account_number>",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": true
947
- },
948
- "50359": {
949
- "content": "<s_supplier_name>",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": true
955
- },
956
- "50360": {
957
- "content": "<s_payment>",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": true
963
- },
964
- "50361": {
965
- "content": "</s_supplier_tax_id>",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": true
971
- },
972
- "50362": {
973
- "content": "</s_invoice_number>",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": true
979
- },
980
- "50363": {
981
- "content": "<s_due_date>",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": true
987
- },
988
- "50364": {
989
- "content": "<s_currency>",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": true
995
- },
996
- "50365": {
997
- "content": "<s_customer_register_id>",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": true
1003
- },
1004
- "50366": {
1005
- "content": "</s_customer_register_id>",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": true
1011
- },
1012
- "50367": {
1013
- "content": "</s_issue_date>",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": true
1019
- },
1020
- "50368": {
1021
- "content": "</s_variable_symbol>",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": true
1027
- },
1028
- "50369": {
1029
- "content": "</s_BIC>",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": true
1035
- },
1036
- "50370": {
1037
- "content": "</s_customer_tax_id>",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": true
1043
- },
1044
- "50371": {
1045
- "content": "</s_total_price>",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": true
1051
- },
1052
- "50372": {
1053
- "content": "</s_IBAN>",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": true
1059
- },
1060
- "50373": {
1061
- "content": "<s_customer_tax_id>",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": true
1067
- },
1068
- "50374": {
1069
- "content": "<s_variable_symbol>",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": true
1075
- },
1076
- "50375": {
1077
- "content": "</s_supplier_register_id>",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": true
1083
- },
1084
- "50376": {
1085
- "content": "</s_currency>",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": true
1091
- },
1092
- "50377": {
1093
- "content": "<s_customer_name>",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": true
1099
- },
1100
- "50378": {
1101
- "content": "</s_supplier_name>",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": true
1107
- },
1108
- "50379": {
1109
- "content": "<s_BIC>",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": true
1115
- },
1116
- "50380": {
1117
- "content": "</s_const_symbol>",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": true
1123
- },
1124
- "50381": {
1125
- "content": "<s_invoice_number>",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": true
1131
- },
1132
- "50382": {
1133
- "content": "<reserved_1>",
1134
- "lstrip": false,
1135
- "normalized": true,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": false
1139
- },
1140
- "50383": {
1141
- "content": "<reserved_2>",
1142
- "lstrip": false,
1143
- "normalized": true,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": false
1147
- },
1148
- "50384": {
1149
- "content": "<reserved_3>",
1150
- "lstrip": false,
1151
- "normalized": true,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": false
1155
- },
1156
- "50385": {
1157
- "content": "<reserved_4>",
1158
- "lstrip": false,
1159
- "normalized": true,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": false
1163
- },
1164
- "50386": {
1165
- "content": "<reserved_5>",
1166
- "lstrip": false,
1167
- "normalized": true,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": false
1171
- },
1172
- "50387": {
1173
- "content": "<reserved_6>",
1174
- "lstrip": false,
1175
- "normalized": true,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": false
1179
- },
1180
- "50388": {
1181
- "content": "<reserved_7>",
1182
- "lstrip": false,
1183
- "normalized": true,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": false
1187
- },
1188
- "50389": {
1189
- "content": "<reserved_8>",
1190
- "lstrip": false,
1191
- "normalized": true,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": false
1195
- },
1196
- "50390": {
1197
- "content": "<reserved_9>",
1198
- "lstrip": false,
1199
- "normalized": true,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": false
1203
- },
1204
- "50391": {
1205
- "content": "<reserved_10>",
1206
- "lstrip": false,
1207
- "normalized": true,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": false
1211
- },
1212
- "50392": {
1213
- "content": "<reserved_11>",
1214
- "lstrip": false,
1215
- "normalized": true,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": false
1219
- },
1220
- "50393": {
1221
- "content": "<reserved_12>",
1222
- "lstrip": false,
1223
- "normalized": true,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": false
1227
- },
1228
- "50394": {
1229
- "content": "<reserved_13>",
1230
- "lstrip": false,
1231
- "normalized": true,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": false
1235
- },
1236
- "50395": {
1237
- "content": "<reserved_14>",
1238
- "lstrip": false,
1239
- "normalized": true,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": false
1243
- },
1244
- "50396": {
1245
- "content": "<reserved_15>",
1246
- "lstrip": false,
1247
- "normalized": true,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": false
1251
- },
1252
- "50397": {
1253
- "content": "<reserved_16>",
1254
- "lstrip": false,
1255
- "normalized": true,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": false
1259
- },
1260
- "50398": {
1261
- "content": "<reserved_17>",
1262
- "lstrip": false,
1263
- "normalized": true,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": false
1267
- },
1268
- "50399": {
1269
- "content": "<reserved_18>",
1270
- "lstrip": false,
1271
- "normalized": true,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": false
1275
- },
1276
- "50400": {
1277
- "content": "<reserved_19>",
1278
- "lstrip": false,
1279
- "normalized": true,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": false
1283
- },
1284
- "50401": {
1285
- "content": "<reserved_20>",
1286
- "lstrip": false,
1287
- "normalized": true,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": false
1291
- },
1292
- "50402": {
1293
- "content": "<reserved_21>",
1294
- "lstrip": false,
1295
- "normalized": true,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": false
1299
- },
1300
- "50403": {
1301
- "content": "<reserved_22>",
1302
- "lstrip": false,
1303
- "normalized": true,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": false
1307
- },
1308
- "50404": {
1309
- "content": "<reserved_23>",
1310
- "lstrip": false,
1311
- "normalized": true,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": false
1315
- },
1316
- "50405": {
1317
- "content": "<reserved_24>",
1318
- "lstrip": false,
1319
- "normalized": true,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": false
1323
- },
1324
- "50406": {
1325
- "content": "<reserved_25>",
1326
- "lstrip": false,
1327
- "normalized": true,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": false
1331
- },
1332
- "50407": {
1333
- "content": "<reserved_26>",
1334
- "lstrip": false,
1335
- "normalized": true,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": false
1339
- },
1340
- "50408": {
1341
- "content": "<reserved_27>",
1342
- "lstrip": false,
1343
- "normalized": true,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": false
1347
- },
1348
- "50409": {
1349
- "content": "<reserved_28>",
1350
- "lstrip": false,
1351
- "normalized": true,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": false
1355
- },
1356
- "50410": {
1357
- "content": "<reserved_29>",
1358
- "lstrip": false,
1359
- "normalized": true,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": false
1363
- },
1364
- "50411": {
1365
- "content": "<reserved_30>",
1366
- "lstrip": false,
1367
- "normalized": true,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": false
1371
- },
1372
- "50412": {
1373
- "content": "<reserved_31>",
1374
- "lstrip": false,
1375
- "normalized": true,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": false
1379
- },
1380
- "50413": {
1381
- "content": "<reserved_32>",
1382
- "lstrip": false,
1383
- "normalized": true,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": false
1387
- },
1388
- "50414": {
1389
- "content": "<reserved_33>",
1390
- "lstrip": false,
1391
- "normalized": true,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": false
1395
- },
1396
- "50415": {
1397
- "content": "<reserved_34>",
1398
- "lstrip": false,
1399
- "normalized": true,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": false
1403
- },
1404
- "50416": {
1405
- "content": "<reserved_35>",
1406
- "lstrip": false,
1407
- "normalized": true,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": false
1411
- },
1412
- "50417": {
1413
- "content": "<reserved_36>",
1414
- "lstrip": false,
1415
- "normalized": true,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": false
1419
- },
1420
- "50418": {
1421
- "content": "<reserved_37>",
1422
- "lstrip": false,
1423
- "normalized": true,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": false
1427
- },
1428
- "50419": {
1429
- "content": "<reserved_38>",
1430
- "lstrip": false,
1431
- "normalized": true,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": false
1435
- },
1436
- "50420": {
1437
- "content": "<reserved_39>",
1438
- "lstrip": false,
1439
- "normalized": true,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": false
1443
- },
1444
- "50421": {
1445
- "content": "<reserved_40>",
1446
- "lstrip": false,
1447
- "normalized": true,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": false
1451
- },
1452
- "50422": {
1453
- "content": "<reserved_41>",
1454
- "lstrip": false,
1455
- "normalized": true,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": false
1459
- },
1460
- "50423": {
1461
- "content": "<reserved_42>",
1462
- "lstrip": false,
1463
- "normalized": true,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": false
1467
- },
1468
- "50424": {
1469
- "content": "<reserved_43>",
1470
- "lstrip": false,
1471
- "normalized": true,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": false
1475
- },
1476
- "50425": {
1477
- "content": "<reserved_44>",
1478
- "lstrip": false,
1479
- "normalized": true,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": false
1483
- },
1484
- "50426": {
1485
- "content": "<reserved_45>",
1486
- "lstrip": false,
1487
- "normalized": true,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": false
1491
- },
1492
- "50427": {
1493
- "content": "<reserved_46>",
1494
- "lstrip": false,
1495
- "normalized": true,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": false
1499
- },
1500
- "50428": {
1501
- "content": "<reserved_47>",
1502
- "lstrip": false,
1503
- "normalized": true,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": false
1507
- },
1508
- "50429": {
1509
- "content": "<reserved_48>",
1510
- "lstrip": false,
1511
- "normalized": true,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": false
1515
- },
1516
- "50430": {
1517
- "content": "<reserved_49>",
1518
- "lstrip": false,
1519
- "normalized": true,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": false
1523
- },
1524
- "50431": {
1525
- "content": "<reserved_50>",
1526
- "lstrip": false,
1527
- "normalized": true,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": false
1531
- }
1532
- },
1533
- "additional_special_tokens": [
1534
- "<s_IBAN>",
1535
- "<s_total_price>",
1536
- "<s_const_symbol>",
1537
- "<s_total_vat>",
1538
- "<s_bank_account_number>",
1539
- "<s_supplier_register_id>",
1540
- "</s_due_date>",
1541
- "<s_supplier_tax_id>",
1542
- "<s_taxable_supply_date>",
1543
- "</s_payment>",
1544
- "</s_total_vat>",
1545
- "</s_customer_name>",
1546
- "</s_taxable_supply_date>",
1547
  "<s_issue_date>",
1548
- "</s_bank_account_number>",
1549
- "<s_supplier_name>",
1550
- "<s_payment>",
1551
- "</s_supplier_tax_id>",
1552
  "</s_invoice_number>",
1553
- "<s_due_date>",
1554
- "<s_currency>",
1555
- "<s_customer_register_id>",
1556
- "</s_customer_register_id>",
1557
- "</s_issue_date>",
1558
  "</s_variable_symbol>",
1559
- "</s_BIC>",
1560
- "</s_customer_tax_id>",
1561
- "</s_total_price>",
1562
- "</s_IBAN>",
1563
- "<s_customer_tax_id>",
 
 
 
 
 
 
 
 
 
 
 
1564
  "<s_variable_symbol>",
1565
- "</s_supplier_register_id>",
1566
- "</s_currency>",
1567
- "<s_customer_name>",
1568
- "</s_supplier_name>",
1569
- "<s_BIC>",
1570
- "</s_const_symbol>",
1571
- "<s_invoice_number>"
1572
  ],
1573
- "clean_up_tokenization_spaces": false,
1574
- "eos_token": "</s>",
1575
- "extra_ids": 100,
1576
- "extra_special_tokens": {},
1577
  "is_vqa": true,
1578
  "model_max_length": 1000000000000000019884624838656,
1579
  "pad_token": "<pad>",
1580
  "processor_class": "Pix2StructProcessor",
1581
  "sp_model_kwargs": {},
1582
  "tokenizer_class": "T5Tokenizer",
1583
- "unk_token": "<unk>",
1584
- "use_fast": true
1585
  }
 
1
  {
2
+ "backend": "tokenizers",
3
+ "eos_token": "</s>",
4
+ "extra_ids": 100,
5
+ "extra_special_tokens": [
6
+ "</s_supp_tax_id>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "<s_issue_date>",
8
+ "</s_bic>",
9
+ "<s_supp_tax_id>",
 
 
10
  "</s_invoice_number>",
11
+ "</s_const_symbol>",
12
+ "<s_cust_register_id>",
13
+ "</s_cust_register_id>",
14
+ "</s_taxable_supply_date>",
15
+ "<s_cust_tax_id>",
16
  "</s_variable_symbol>",
17
+ "</s_issue_date>",
18
+ "</s_cust_tax_id>",
19
+ "<s_invoice_number>",
20
+ "<s_taxable_supply_date>",
21
+ "<s_supp_register_id>",
22
+ "<s_payment_type>",
23
+ "<s_bic>",
24
+ "</s_bank_account_number>",
25
+ "</s_total>",
26
+ "</s_payment_type>",
27
+ "<s_bank_account_number>",
28
+ "<s_iban>",
29
+ "</s_iban>",
30
+ "</s_supp_register_id>",
31
+ "<s_const_symbol>",
32
+ "<s_total>",
33
  "<s_variable_symbol>",
34
+ "</s_due_date>",
35
+ "<s_due_date>"
 
 
 
 
 
36
  ],
37
+ "is_local": false,
 
 
 
38
  "is_vqa": true,
39
  "model_max_length": 1000000000000000019884624838656,
40
  "pad_token": "<pad>",
41
  "processor_class": "Pix2StructProcessor",
42
  "sp_model_kwargs": {},
43
  "tokenizer_class": "T5Tokenizer",
44
+ "unk_token": "<unk>"
 
45
  }