TomasFAV commited on
Commit
b741a82
·
verified ·
1 Parent(s): adc2367

Upload processor

Browse files
added_tokens.json CHANGED
@@ -1,90 +1,26 @@
1
  {
2
- "</s_BIC>": 50344,
3
- "</s_IBAN>": 50349,
4
- "</s_bank_account_number>": 50345,
5
- "</s_const_symbol>": 50362,
6
- "</s_currency>": 50353,
7
- "</s_customer_name>": 50351,
8
- "</s_customer_register_id>": 50352,
9
- "</s_customer_tax_id>": 50373,
10
- "</s_due_date>": 50361,
11
- "</s_invoice_number>": 50375,
12
- "</s_issue_date>": 50350,
13
- "</s_payment>": 50368,
14
- "</s_supplier_name>": 50366,
15
- "</s_supplier_register_id>": 50356,
16
- "</s_supplier_tax_id>": 50380,
17
- "</s_taxable_supply_date>": 50358,
18
- "</s_total_price>": 50354,
19
- "</s_total_vat>": 50357,
20
- "</s_variable_symbol>": 50359,
21
- "<reserved_10>": 50391,
22
- "<reserved_11>": 50392,
23
- "<reserved_12>": 50393,
24
- "<reserved_13>": 50394,
25
- "<reserved_14>": 50395,
26
- "<reserved_15>": 50396,
27
- "<reserved_16>": 50397,
28
- "<reserved_17>": 50398,
29
- "<reserved_18>": 50399,
30
- "<reserved_19>": 50400,
31
- "<reserved_1>": 50382,
32
- "<reserved_20>": 50401,
33
- "<reserved_21>": 50402,
34
- "<reserved_22>": 50403,
35
- "<reserved_23>": 50404,
36
- "<reserved_24>": 50405,
37
- "<reserved_25>": 50406,
38
- "<reserved_26>": 50407,
39
- "<reserved_27>": 50408,
40
- "<reserved_28>": 50409,
41
- "<reserved_29>": 50410,
42
- "<reserved_2>": 50383,
43
- "<reserved_30>": 50411,
44
- "<reserved_31>": 50412,
45
- "<reserved_32>": 50413,
46
- "<reserved_33>": 50414,
47
- "<reserved_34>": 50415,
48
- "<reserved_35>": 50416,
49
- "<reserved_36>": 50417,
50
- "<reserved_37>": 50418,
51
- "<reserved_38>": 50419,
52
- "<reserved_39>": 50420,
53
- "<reserved_3>": 50384,
54
- "<reserved_40>": 50421,
55
- "<reserved_41>": 50422,
56
- "<reserved_42>": 50423,
57
- "<reserved_43>": 50424,
58
- "<reserved_44>": 50425,
59
- "<reserved_45>": 50426,
60
- "<reserved_46>": 50427,
61
- "<reserved_47>": 50428,
62
- "<reserved_48>": 50429,
63
- "<reserved_49>": 50430,
64
- "<reserved_4>": 50385,
65
- "<reserved_50>": 50431,
66
- "<reserved_5>": 50386,
67
- "<reserved_6>": 50387,
68
- "<reserved_7>": 50388,
69
- "<reserved_8>": 50389,
70
- "<reserved_9>": 50390,
71
- "<s_BIC>": 50369,
72
- "<s_IBAN>": 50371,
73
- "<s_bank_account_number>": 50360,
74
- "<s_const_symbol>": 50365,
75
- "<s_currency>": 50346,
76
- "<s_customer_name>": 50347,
77
- "<s_customer_register_id>": 50381,
78
- "<s_customer_tax_id>": 50378,
79
- "<s_due_date>": 50363,
80
- "<s_invoice_number>": 50379,
81
- "<s_issue_date>": 50370,
82
- "<s_payment>": 50377,
83
- "<s_supplier_name>": 50355,
84
- "<s_supplier_register_id>": 50372,
85
- "<s_supplier_tax_id>": 50376,
86
- "<s_taxable_supply_date>": 50348,
87
- "<s_total_price>": 50364,
88
- "<s_total_vat>": 50367,
89
- "<s_variable_symbol>": 50374
90
  }
 
1
  {
2
+ "<reserved_10>": 50353,
3
+ "<reserved_11>": 50354,
4
+ "<reserved_12>": 50355,
5
+ "<reserved_13>": 50356,
6
+ "<reserved_14>": 50357,
7
+ "<reserved_15>": 50358,
8
+ "<reserved_16>": 50359,
9
+ "<reserved_17>": 50360,
10
+ "<reserved_18>": 50361,
11
+ "<reserved_19>": 50362,
12
+ "<reserved_1>": 50344,
13
+ "<reserved_20>": 50363,
14
+ "<reserved_21>": 50364,
15
+ "<reserved_22>": 50365,
16
+ "<reserved_23>": 50366,
17
+ "<reserved_24>": 50367,
18
+ "<reserved_2>": 50345,
19
+ "<reserved_3>": 50346,
20
+ "<reserved_4>": 50347,
21
+ "<reserved_5>": 50348,
22
+ "<reserved_6>": 50349,
23
+ "<reserved_7>": 50350,
24
+ "<reserved_8>": 50351,
25
+ "<reserved_9>": 50352
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
preprocessor_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "do_normalize": true,
4
  "image_processor_type": "Pix2StructImageProcessor",
5
  "is_vqa": false,
6
- "max_patches": 1536,
7
  "patch_size": {
8
  "height": 16,
9
  "width": 16
 
3
  "do_normalize": true,
4
  "image_processor_type": "Pix2StructImageProcessor",
5
  "is_vqa": false,
6
+ "max_patches": 2048,
7
  "patch_size": {
8
  "height": 16,
9
  "width": 16
special_tokens_map.json CHANGED
@@ -1,271 +1,105 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "</s_BIC>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "</s_bank_account_number>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "<s_currency>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "<s_customer_name>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "<s_taxable_supply_date>",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- {
39
- "content": "</s_IBAN>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- {
46
- "content": "</s_issue_date>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false
51
- },
52
- {
53
- "content": "</s_customer_name>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false
58
- },
59
- {
60
- "content": "</s_customer_register_id>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false
65
- },
66
- {
67
- "content": "</s_currency>",
68
- "lstrip": false,
69
- "normalized": false,
70
- "rstrip": false,
71
- "single_word": false
72
- },
73
- {
74
- "content": "</s_total_price>",
75
- "lstrip": false,
76
- "normalized": false,
77
- "rstrip": false,
78
- "single_word": false
79
- },
80
- {
81
- "content": "<s_supplier_name>",
82
- "lstrip": false,
83
- "normalized": false,
84
- "rstrip": false,
85
- "single_word": false
86
- },
87
- {
88
- "content": "</s_supplier_register_id>",
89
- "lstrip": false,
90
- "normalized": false,
91
- "rstrip": false,
92
- "single_word": false
93
- },
94
- {
95
- "content": "</s_total_vat>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": false,
99
- "single_word": false
100
- },
101
- {
102
- "content": "</s_taxable_supply_date>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false
107
- },
108
- {
109
- "content": "</s_variable_symbol>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false
114
- },
115
- {
116
- "content": "<s_bank_account_number>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false
121
- },
122
- {
123
- "content": "</s_due_date>",
124
- "lstrip": false,
125
- "normalized": false,
126
- "rstrip": false,
127
- "single_word": false
128
- },
129
- {
130
- "content": "</s_const_symbol>",
131
- "lstrip": false,
132
- "normalized": false,
133
- "rstrip": false,
134
- "single_word": false
135
- },
136
- {
137
- "content": "<s_due_date>",
138
- "lstrip": false,
139
- "normalized": false,
140
- "rstrip": false,
141
- "single_word": false
142
- },
143
- {
144
- "content": "<s_total_price>",
145
- "lstrip": false,
146
- "normalized": false,
147
- "rstrip": false,
148
- "single_word": false
149
- },
150
- {
151
- "content": "<s_const_symbol>",
152
- "lstrip": false,
153
- "normalized": false,
154
- "rstrip": false,
155
- "single_word": false
156
- },
157
- {
158
- "content": "</s_supplier_name>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false
163
- },
164
- {
165
- "content": "<s_total_vat>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false
170
- },
171
- {
172
- "content": "</s_payment>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false
177
- },
178
- {
179
- "content": "<s_BIC>",
180
- "lstrip": false,
181
- "normalized": false,
182
- "rstrip": false,
183
- "single_word": false
184
- },
185
- {
186
- "content": "<s_issue_date>",
187
- "lstrip": false,
188
- "normalized": false,
189
- "rstrip": false,
190
- "single_word": false
191
- },
192
- {
193
- "content": "<s_IBAN>",
194
- "lstrip": false,
195
- "normalized": false,
196
- "rstrip": false,
197
- "single_word": false
198
- },
199
- {
200
- "content": "<s_supplier_register_id>",
201
- "lstrip": false,
202
- "normalized": false,
203
- "rstrip": false,
204
- "single_word": false
205
- },
206
- {
207
- "content": "</s_customer_tax_id>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false
212
- },
213
- {
214
- "content": "<s_variable_symbol>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false
219
- },
220
- {
221
- "content": "</s_invoice_number>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false
226
- },
227
- {
228
- "content": "<s_supplier_tax_id>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false
233
- },
234
- {
235
- "content": "<s_payment>",
236
- "lstrip": false,
237
- "normalized": false,
238
- "rstrip": false,
239
- "single_word": false
240
- },
241
- {
242
- "content": "<s_customer_tax_id>",
243
- "lstrip": false,
244
- "normalized": false,
245
- "rstrip": false,
246
- "single_word": false
247
- },
248
- {
249
- "content": "<s_invoice_number>",
250
- "lstrip": false,
251
- "normalized": false,
252
- "rstrip": false,
253
- "single_word": false
254
- },
255
- {
256
- "content": "</s_supplier_tax_id>",
257
- "lstrip": false,
258
- "normalized": false,
259
- "rstrip": false,
260
- "single_word": false
261
- },
262
- {
263
- "content": "<s_customer_register_id>",
264
- "lstrip": false,
265
- "normalized": false,
266
- "rstrip": false,
267
- "single_word": false
268
- }
269
  ],
270
  "eos_token": {
271
  "content": "</s>",
 
1
  {
2
  "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  ],
104
  "eos_token": {
105
  "content": "</s>",
tokenizer.json CHANGED
@@ -941,348 +941,6 @@
941
  },
942
  {
943
  "id": 50344,
944
- "content": "</s_BIC>",
945
- "single_word": false,
946
- "lstrip": false,
947
- "rstrip": false,
948
- "normalized": false,
949
- "special": true
950
- },
951
- {
952
- "id": 50345,
953
- "content": "</s_bank_account_number>",
954
- "single_word": false,
955
- "lstrip": false,
956
- "rstrip": false,
957
- "normalized": false,
958
- "special": true
959
- },
960
- {
961
- "id": 50346,
962
- "content": "<s_currency>",
963
- "single_word": false,
964
- "lstrip": false,
965
- "rstrip": false,
966
- "normalized": false,
967
- "special": true
968
- },
969
- {
970
- "id": 50347,
971
- "content": "<s_customer_name>",
972
- "single_word": false,
973
- "lstrip": false,
974
- "rstrip": false,
975
- "normalized": false,
976
- "special": true
977
- },
978
- {
979
- "id": 50348,
980
- "content": "<s_taxable_supply_date>",
981
- "single_word": false,
982
- "lstrip": false,
983
- "rstrip": false,
984
- "normalized": false,
985
- "special": true
986
- },
987
- {
988
- "id": 50349,
989
- "content": "</s_IBAN>",
990
- "single_word": false,
991
- "lstrip": false,
992
- "rstrip": false,
993
- "normalized": false,
994
- "special": true
995
- },
996
- {
997
- "id": 50350,
998
- "content": "</s_issue_date>",
999
- "single_word": false,
1000
- "lstrip": false,
1001
- "rstrip": false,
1002
- "normalized": false,
1003
- "special": true
1004
- },
1005
- {
1006
- "id": 50351,
1007
- "content": "</s_customer_name>",
1008
- "single_word": false,
1009
- "lstrip": false,
1010
- "rstrip": false,
1011
- "normalized": false,
1012
- "special": true
1013
- },
1014
- {
1015
- "id": 50352,
1016
- "content": "</s_customer_register_id>",
1017
- "single_word": false,
1018
- "lstrip": false,
1019
- "rstrip": false,
1020
- "normalized": false,
1021
- "special": true
1022
- },
1023
- {
1024
- "id": 50353,
1025
- "content": "</s_currency>",
1026
- "single_word": false,
1027
- "lstrip": false,
1028
- "rstrip": false,
1029
- "normalized": false,
1030
- "special": true
1031
- },
1032
- {
1033
- "id": 50354,
1034
- "content": "</s_total_price>",
1035
- "single_word": false,
1036
- "lstrip": false,
1037
- "rstrip": false,
1038
- "normalized": false,
1039
- "special": true
1040
- },
1041
- {
1042
- "id": 50355,
1043
- "content": "<s_supplier_name>",
1044
- "single_word": false,
1045
- "lstrip": false,
1046
- "rstrip": false,
1047
- "normalized": false,
1048
- "special": true
1049
- },
1050
- {
1051
- "id": 50356,
1052
- "content": "</s_supplier_register_id>",
1053
- "single_word": false,
1054
- "lstrip": false,
1055
- "rstrip": false,
1056
- "normalized": false,
1057
- "special": true
1058
- },
1059
- {
1060
- "id": 50357,
1061
- "content": "</s_total_vat>",
1062
- "single_word": false,
1063
- "lstrip": false,
1064
- "rstrip": false,
1065
- "normalized": false,
1066
- "special": true
1067
- },
1068
- {
1069
- "id": 50358,
1070
- "content": "</s_taxable_supply_date>",
1071
- "single_word": false,
1072
- "lstrip": false,
1073
- "rstrip": false,
1074
- "normalized": false,
1075
- "special": true
1076
- },
1077
- {
1078
- "id": 50359,
1079
- "content": "</s_variable_symbol>",
1080
- "single_word": false,
1081
- "lstrip": false,
1082
- "rstrip": false,
1083
- "normalized": false,
1084
- "special": true
1085
- },
1086
- {
1087
- "id": 50360,
1088
- "content": "<s_bank_account_number>",
1089
- "single_word": false,
1090
- "lstrip": false,
1091
- "rstrip": false,
1092
- "normalized": false,
1093
- "special": true
1094
- },
1095
- {
1096
- "id": 50361,
1097
- "content": "</s_due_date>",
1098
- "single_word": false,
1099
- "lstrip": false,
1100
- "rstrip": false,
1101
- "normalized": false,
1102
- "special": true
1103
- },
1104
- {
1105
- "id": 50362,
1106
- "content": "</s_const_symbol>",
1107
- "single_word": false,
1108
- "lstrip": false,
1109
- "rstrip": false,
1110
- "normalized": false,
1111
- "special": true
1112
- },
1113
- {
1114
- "id": 50363,
1115
- "content": "<s_due_date>",
1116
- "single_word": false,
1117
- "lstrip": false,
1118
- "rstrip": false,
1119
- "normalized": false,
1120
- "special": true
1121
- },
1122
- {
1123
- "id": 50364,
1124
- "content": "<s_total_price>",
1125
- "single_word": false,
1126
- "lstrip": false,
1127
- "rstrip": false,
1128
- "normalized": false,
1129
- "special": true
1130
- },
1131
- {
1132
- "id": 50365,
1133
- "content": "<s_const_symbol>",
1134
- "single_word": false,
1135
- "lstrip": false,
1136
- "rstrip": false,
1137
- "normalized": false,
1138
- "special": true
1139
- },
1140
- {
1141
- "id": 50366,
1142
- "content": "</s_supplier_name>",
1143
- "single_word": false,
1144
- "lstrip": false,
1145
- "rstrip": false,
1146
- "normalized": false,
1147
- "special": true
1148
- },
1149
- {
1150
- "id": 50367,
1151
- "content": "<s_total_vat>",
1152
- "single_word": false,
1153
- "lstrip": false,
1154
- "rstrip": false,
1155
- "normalized": false,
1156
- "special": true
1157
- },
1158
- {
1159
- "id": 50368,
1160
- "content": "</s_payment>",
1161
- "single_word": false,
1162
- "lstrip": false,
1163
- "rstrip": false,
1164
- "normalized": false,
1165
- "special": true
1166
- },
1167
- {
1168
- "id": 50369,
1169
- "content": "<s_BIC>",
1170
- "single_word": false,
1171
- "lstrip": false,
1172
- "rstrip": false,
1173
- "normalized": false,
1174
- "special": true
1175
- },
1176
- {
1177
- "id": 50370,
1178
- "content": "<s_issue_date>",
1179
- "single_word": false,
1180
- "lstrip": false,
1181
- "rstrip": false,
1182
- "normalized": false,
1183
- "special": true
1184
- },
1185
- {
1186
- "id": 50371,
1187
- "content": "<s_IBAN>",
1188
- "single_word": false,
1189
- "lstrip": false,
1190
- "rstrip": false,
1191
- "normalized": false,
1192
- "special": true
1193
- },
1194
- {
1195
- "id": 50372,
1196
- "content": "<s_supplier_register_id>",
1197
- "single_word": false,
1198
- "lstrip": false,
1199
- "rstrip": false,
1200
- "normalized": false,
1201
- "special": true
1202
- },
1203
- {
1204
- "id": 50373,
1205
- "content": "</s_customer_tax_id>",
1206
- "single_word": false,
1207
- "lstrip": false,
1208
- "rstrip": false,
1209
- "normalized": false,
1210
- "special": true
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_invoice_number>",
1224
- "single_word": false,
1225
- "lstrip": false,
1226
- "rstrip": false,
1227
- "normalized": false,
1228
- "special": true
1229
- },
1230
- {
1231
- "id": 50376,
1232
- "content": "<s_supplier_tax_id>",
1233
- "single_word": false,
1234
- "lstrip": false,
1235
- "rstrip": false,
1236
- "normalized": false,
1237
- "special": true
1238
- },
1239
- {
1240
- "id": 50377,
1241
- "content": "<s_payment>",
1242
- "single_word": false,
1243
- "lstrip": false,
1244
- "rstrip": false,
1245
- "normalized": false,
1246
- "special": true
1247
- },
1248
- {
1249
- "id": 50378,
1250
- "content": "<s_customer_tax_id>",
1251
- "single_word": false,
1252
- "lstrip": false,
1253
- "rstrip": false,
1254
- "normalized": false,
1255
- "special": true
1256
- },
1257
- {
1258
- "id": 50379,
1259
- "content": "<s_invoice_number>",
1260
- "single_word": false,
1261
- "lstrip": false,
1262
- "rstrip": false,
1263
- "normalized": false,
1264
- "special": true
1265
- },
1266
- {
1267
- "id": 50380,
1268
- "content": "</s_supplier_tax_id>",
1269
- "single_word": false,
1270
- "lstrip": false,
1271
- "rstrip": false,
1272
- "normalized": false,
1273
- "special": true
1274
- },
1275
- {
1276
- "id": 50381,
1277
- "content": "<s_customer_register_id>",
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,
@@ -1291,7 +949,7 @@
1291
  "special": false
1292
  },
1293
  {
1294
- "id": 50383,
1295
  "content": "<reserved_2>",
1296
  "single_word": false,
1297
  "lstrip": false,
@@ -1300,7 +958,7 @@
1300
  "special": false
1301
  },
1302
  {
1303
- "id": 50384,
1304
  "content": "<reserved_3>",
1305
  "single_word": false,
1306
  "lstrip": false,
@@ -1309,7 +967,7 @@
1309
  "special": false
1310
  },
1311
  {
1312
- "id": 50385,
1313
  "content": "<reserved_4>",
1314
  "single_word": false,
1315
  "lstrip": false,
@@ -1318,7 +976,7 @@
1318
  "special": false
1319
  },
1320
  {
1321
- "id": 50386,
1322
  "content": "<reserved_5>",
1323
  "single_word": false,
1324
  "lstrip": false,
@@ -1327,7 +985,7 @@
1327
  "special": false
1328
  },
1329
  {
1330
- "id": 50387,
1331
  "content": "<reserved_6>",
1332
  "single_word": false,
1333
  "lstrip": false,
@@ -1336,7 +994,7 @@
1336
  "special": false
1337
  },
1338
  {
1339
- "id": 50388,
1340
  "content": "<reserved_7>",
1341
  "single_word": false,
1342
  "lstrip": false,
@@ -1345,7 +1003,7 @@
1345
  "special": false
1346
  },
1347
  {
1348
- "id": 50389,
1349
  "content": "<reserved_8>",
1350
  "single_word": false,
1351
  "lstrip": false,
@@ -1354,7 +1012,7 @@
1354
  "special": false
1355
  },
1356
  {
1357
- "id": 50390,
1358
  "content": "<reserved_9>",
1359
  "single_word": false,
1360
  "lstrip": false,
@@ -1363,7 +1021,7 @@
1363
  "special": false
1364
  },
1365
  {
1366
- "id": 50391,
1367
  "content": "<reserved_10>",
1368
  "single_word": false,
1369
  "lstrip": false,
@@ -1372,7 +1030,7 @@
1372
  "special": false
1373
  },
1374
  {
1375
- "id": 50392,
1376
  "content": "<reserved_11>",
1377
  "single_word": false,
1378
  "lstrip": false,
@@ -1381,7 +1039,7 @@
1381
  "special": false
1382
  },
1383
  {
1384
- "id": 50393,
1385
  "content": "<reserved_12>",
1386
  "single_word": false,
1387
  "lstrip": false,
@@ -1390,7 +1048,7 @@
1390
  "special": false
1391
  },
1392
  {
1393
- "id": 50394,
1394
  "content": "<reserved_13>",
1395
  "single_word": false,
1396
  "lstrip": false,
@@ -1399,7 +1057,7 @@
1399
  "special": false
1400
  },
1401
  {
1402
- "id": 50395,
1403
  "content": "<reserved_14>",
1404
  "single_word": false,
1405
  "lstrip": false,
@@ -1408,7 +1066,7 @@
1408
  "special": false
1409
  },
1410
  {
1411
- "id": 50396,
1412
  "content": "<reserved_15>",
1413
  "single_word": false,
1414
  "lstrip": false,
@@ -1417,7 +1075,7 @@
1417
  "special": false
1418
  },
1419
  {
1420
- "id": 50397,
1421
  "content": "<reserved_16>",
1422
  "single_word": false,
1423
  "lstrip": false,
@@ -1426,7 +1084,7 @@
1426
  "special": false
1427
  },
1428
  {
1429
- "id": 50398,
1430
  "content": "<reserved_17>",
1431
  "single_word": false,
1432
  "lstrip": false,
@@ -1435,7 +1093,7 @@
1435
  "special": false
1436
  },
1437
  {
1438
- "id": 50399,
1439
  "content": "<reserved_18>",
1440
  "single_word": false,
1441
  "lstrip": false,
@@ -1444,7 +1102,7 @@
1444
  "special": false
1445
  },
1446
  {
1447
- "id": 50400,
1448
  "content": "<reserved_19>",
1449
  "single_word": false,
1450
  "lstrip": false,
@@ -1453,7 +1111,7 @@
1453
  "special": false
1454
  },
1455
  {
1456
- "id": 50401,
1457
  "content": "<reserved_20>",
1458
  "single_word": false,
1459
  "lstrip": false,
@@ -1462,7 +1120,7 @@
1462
  "special": false
1463
  },
1464
  {
1465
- "id": 50402,
1466
  "content": "<reserved_21>",
1467
  "single_word": false,
1468
  "lstrip": false,
@@ -1471,7 +1129,7 @@
1471
  "special": false
1472
  },
1473
  {
1474
- "id": 50403,
1475
  "content": "<reserved_22>",
1476
  "single_word": false,
1477
  "lstrip": false,
@@ -1480,7 +1138,7 @@
1480
  "special": false
1481
  },
1482
  {
1483
- "id": 50404,
1484
  "content": "<reserved_23>",
1485
  "single_word": false,
1486
  "lstrip": false,
@@ -1489,247 +1147,13 @@
1489
  "special": false
1490
  },
1491
  {
1492
- "id": 50405,
1493
  "content": "<reserved_24>",
1494
  "single_word": false,
1495
  "lstrip": false,
1496
  "rstrip": false,
1497
  "normalized": true,
1498
  "special": false
1499
- },
1500
- {
1501
- "id": 50406,
1502
- "content": "<reserved_25>",
1503
- "single_word": false,
1504
- "lstrip": false,
1505
- "rstrip": false,
1506
- "normalized": true,
1507
- "special": false
1508
- },
1509
- {
1510
- "id": 50407,
1511
- "content": "<reserved_26>",
1512
- "single_word": false,
1513
- "lstrip": false,
1514
- "rstrip": false,
1515
- "normalized": true,
1516
- "special": false
1517
- },
1518
- {
1519
- "id": 50408,
1520
- "content": "<reserved_27>",
1521
- "single_word": false,
1522
- "lstrip": false,
1523
- "rstrip": false,
1524
- "normalized": true,
1525
- "special": false
1526
- },
1527
- {
1528
- "id": 50409,
1529
- "content": "<reserved_28>",
1530
- "single_word": false,
1531
- "lstrip": false,
1532
- "rstrip": false,
1533
- "normalized": true,
1534
- "special": false
1535
- },
1536
- {
1537
- "id": 50410,
1538
- "content": "<reserved_29>",
1539
- "single_word": false,
1540
- "lstrip": false,
1541
- "rstrip": false,
1542
- "normalized": true,
1543
- "special": false
1544
- },
1545
- {
1546
- "id": 50411,
1547
- "content": "<reserved_30>",
1548
- "single_word": false,
1549
- "lstrip": false,
1550
- "rstrip": false,
1551
- "normalized": true,
1552
- "special": false
1553
- },
1554
- {
1555
- "id": 50412,
1556
- "content": "<reserved_31>",
1557
- "single_word": false,
1558
- "lstrip": false,
1559
- "rstrip": false,
1560
- "normalized": true,
1561
- "special": false
1562
- },
1563
- {
1564
- "id": 50413,
1565
- "content": "<reserved_32>",
1566
- "single_word": false,
1567
- "lstrip": false,
1568
- "rstrip": false,
1569
- "normalized": true,
1570
- "special": false
1571
- },
1572
- {
1573
- "id": 50414,
1574
- "content": "<reserved_33>",
1575
- "single_word": false,
1576
- "lstrip": false,
1577
- "rstrip": false,
1578
- "normalized": true,
1579
- "special": false
1580
- },
1581
- {
1582
- "id": 50415,
1583
- "content": "<reserved_34>",
1584
- "single_word": false,
1585
- "lstrip": false,
1586
- "rstrip": false,
1587
- "normalized": true,
1588
- "special": false
1589
- },
1590
- {
1591
- "id": 50416,
1592
- "content": "<reserved_35>",
1593
- "single_word": false,
1594
- "lstrip": false,
1595
- "rstrip": false,
1596
- "normalized": true,
1597
- "special": false
1598
- },
1599
- {
1600
- "id": 50417,
1601
- "content": "<reserved_36>",
1602
- "single_word": false,
1603
- "lstrip": false,
1604
- "rstrip": false,
1605
- "normalized": true,
1606
- "special": false
1607
- },
1608
- {
1609
- "id": 50418,
1610
- "content": "<reserved_37>",
1611
- "single_word": false,
1612
- "lstrip": false,
1613
- "rstrip": false,
1614
- "normalized": true,
1615
- "special": false
1616
- },
1617
- {
1618
- "id": 50419,
1619
- "content": "<reserved_38>",
1620
- "single_word": false,
1621
- "lstrip": false,
1622
- "rstrip": false,
1623
- "normalized": true,
1624
- "special": false
1625
- },
1626
- {
1627
- "id": 50420,
1628
- "content": "<reserved_39>",
1629
- "single_word": false,
1630
- "lstrip": false,
1631
- "rstrip": false,
1632
- "normalized": true,
1633
- "special": false
1634
- },
1635
- {
1636
- "id": 50421,
1637
- "content": "<reserved_40>",
1638
- "single_word": false,
1639
- "lstrip": false,
1640
- "rstrip": false,
1641
- "normalized": true,
1642
- "special": false
1643
- },
1644
- {
1645
- "id": 50422,
1646
- "content": "<reserved_41>",
1647
- "single_word": false,
1648
- "lstrip": false,
1649
- "rstrip": false,
1650
- "normalized": true,
1651
- "special": false
1652
- },
1653
- {
1654
- "id": 50423,
1655
- "content": "<reserved_42>",
1656
- "single_word": false,
1657
- "lstrip": false,
1658
- "rstrip": false,
1659
- "normalized": true,
1660
- "special": false
1661
- },
1662
- {
1663
- "id": 50424,
1664
- "content": "<reserved_43>",
1665
- "single_word": false,
1666
- "lstrip": false,
1667
- "rstrip": false,
1668
- "normalized": true,
1669
- "special": false
1670
- },
1671
- {
1672
- "id": 50425,
1673
- "content": "<reserved_44>",
1674
- "single_word": false,
1675
- "lstrip": false,
1676
- "rstrip": false,
1677
- "normalized": true,
1678
- "special": false
1679
- },
1680
- {
1681
- "id": 50426,
1682
- "content": "<reserved_45>",
1683
- "single_word": false,
1684
- "lstrip": false,
1685
- "rstrip": false,
1686
- "normalized": true,
1687
- "special": false
1688
- },
1689
- {
1690
- "id": 50427,
1691
- "content": "<reserved_46>",
1692
- "single_word": false,
1693
- "lstrip": false,
1694
- "rstrip": false,
1695
- "normalized": true,
1696
- "special": false
1697
- },
1698
- {
1699
- "id": 50428,
1700
- "content": "<reserved_47>",
1701
- "single_word": false,
1702
- "lstrip": false,
1703
- "rstrip": false,
1704
- "normalized": true,
1705
- "special": false
1706
- },
1707
- {
1708
- "id": 50429,
1709
- "content": "<reserved_48>",
1710
- "single_word": false,
1711
- "lstrip": false,
1712
- "rstrip": false,
1713
- "normalized": true,
1714
- "special": false
1715
- },
1716
- {
1717
- "id": 50430,
1718
- "content": "<reserved_49>",
1719
- "single_word": false,
1720
- "lstrip": false,
1721
- "rstrip": false,
1722
- "normalized": true,
1723
- "special": false
1724
- },
1725
- {
1726
- "id": 50431,
1727
- "content": "<reserved_50>",
1728
- "single_word": false,
1729
- "lstrip": false,
1730
- "rstrip": false,
1731
- "normalized": true,
1732
- "special": false
1733
  }
1734
  ],
1735
  "normalizer": {
 
941
  },
942
  {
943
  "id": 50344,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
944
  "content": "<reserved_1>",
945
  "single_word": false,
946
  "lstrip": false,
 
949
  "special": false
950
  },
951
  {
952
+ "id": 50345,
953
  "content": "<reserved_2>",
954
  "single_word": false,
955
  "lstrip": false,
 
958
  "special": false
959
  },
960
  {
961
+ "id": 50346,
962
  "content": "<reserved_3>",
963
  "single_word": false,
964
  "lstrip": false,
 
967
  "special": false
968
  },
969
  {
970
+ "id": 50347,
971
  "content": "<reserved_4>",
972
  "single_word": false,
973
  "lstrip": false,
 
976
  "special": false
977
  },
978
  {
979
+ "id": 50348,
980
  "content": "<reserved_5>",
981
  "single_word": false,
982
  "lstrip": false,
 
985
  "special": false
986
  },
987
  {
988
+ "id": 50349,
989
  "content": "<reserved_6>",
990
  "single_word": false,
991
  "lstrip": false,
 
994
  "special": false
995
  },
996
  {
997
+ "id": 50350,
998
  "content": "<reserved_7>",
999
  "single_word": false,
1000
  "lstrip": false,
 
1003
  "special": false
1004
  },
1005
  {
1006
+ "id": 50351,
1007
  "content": "<reserved_8>",
1008
  "single_word": false,
1009
  "lstrip": false,
 
1012
  "special": false
1013
  },
1014
  {
1015
+ "id": 50352,
1016
  "content": "<reserved_9>",
1017
  "single_word": false,
1018
  "lstrip": false,
 
1021
  "special": false
1022
  },
1023
  {
1024
+ "id": 50353,
1025
  "content": "<reserved_10>",
1026
  "single_word": false,
1027
  "lstrip": false,
 
1030
  "special": false
1031
  },
1032
  {
1033
+ "id": 50354,
1034
  "content": "<reserved_11>",
1035
  "single_word": false,
1036
  "lstrip": false,
 
1039
  "special": false
1040
  },
1041
  {
1042
+ "id": 50355,
1043
  "content": "<reserved_12>",
1044
  "single_word": false,
1045
  "lstrip": false,
 
1048
  "special": false
1049
  },
1050
  {
1051
+ "id": 50356,
1052
  "content": "<reserved_13>",
1053
  "single_word": false,
1054
  "lstrip": false,
 
1057
  "special": false
1058
  },
1059
  {
1060
+ "id": 50357,
1061
  "content": "<reserved_14>",
1062
  "single_word": false,
1063
  "lstrip": false,
 
1066
  "special": false
1067
  },
1068
  {
1069
+ "id": 50358,
1070
  "content": "<reserved_15>",
1071
  "single_word": false,
1072
  "lstrip": false,
 
1075
  "special": false
1076
  },
1077
  {
1078
+ "id": 50359,
1079
  "content": "<reserved_16>",
1080
  "single_word": false,
1081
  "lstrip": false,
 
1084
  "special": false
1085
  },
1086
  {
1087
+ "id": 50360,
1088
  "content": "<reserved_17>",
1089
  "single_word": false,
1090
  "lstrip": false,
 
1093
  "special": false
1094
  },
1095
  {
1096
+ "id": 50361,
1097
  "content": "<reserved_18>",
1098
  "single_word": false,
1099
  "lstrip": false,
 
1102
  "special": false
1103
  },
1104
  {
1105
+ "id": 50362,
1106
  "content": "<reserved_19>",
1107
  "single_word": false,
1108
  "lstrip": false,
 
1111
  "special": false
1112
  },
1113
  {
1114
+ "id": 50363,
1115
  "content": "<reserved_20>",
1116
  "single_word": false,
1117
  "lstrip": false,
 
1120
  "special": false
1121
  },
1122
  {
1123
+ "id": 50364,
1124
  "content": "<reserved_21>",
1125
  "single_word": false,
1126
  "lstrip": false,
 
1129
  "special": false
1130
  },
1131
  {
1132
+ "id": 50365,
1133
  "content": "<reserved_22>",
1134
  "single_word": false,
1135
  "lstrip": false,
 
1138
  "special": false
1139
  },
1140
  {
1141
+ "id": 50366,
1142
  "content": "<reserved_23>",
1143
  "single_word": false,
1144
  "lstrip": false,
 
1147
  "special": false
1148
  },
1149
  {
1150
+ "id": 50367,
1151
  "content": "<reserved_24>",
1152
  "single_word": false,
1153
  "lstrip": false,
1154
  "rstrip": false,
1155
  "normalized": true,
1156
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1157
  }
1158
  ],
1159
  "normalizer": {
tokenizer_config.json CHANGED
@@ -826,310 +826,6 @@
826
  "special": true
827
  },
828
  "50344": {
829
- "content": "</s_BIC>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": true
835
- },
836
- "50345": {
837
- "content": "</s_bank_account_number>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": true
843
- },
844
- "50346": {
845
- "content": "<s_currency>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": true
851
- },
852
- "50347": {
853
- "content": "<s_customer_name>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "50348": {
861
- "content": "<s_taxable_supply_date>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "50349": {
869
- "content": "</s_IBAN>",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": true
875
- },
876
- "50350": {
877
- "content": "</s_issue_date>",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": true
883
- },
884
- "50351": {
885
- "content": "</s_customer_name>",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": true
891
- },
892
- "50352": {
893
- "content": "</s_customer_register_id>",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": true
899
- },
900
- "50353": {
901
- "content": "</s_currency>",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": true
907
- },
908
- "50354": {
909
- "content": "</s_total_price>",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": true
915
- },
916
- "50355": {
917
- "content": "<s_supplier_name>",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": true
923
- },
924
- "50356": {
925
- "content": "</s_supplier_register_id>",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": true
931
- },
932
- "50357": {
933
- "content": "</s_total_vat>",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": true
939
- },
940
- "50358": {
941
- "content": "</s_taxable_supply_date>",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": true
947
- },
948
- "50359": {
949
- "content": "</s_variable_symbol>",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": true
955
- },
956
- "50360": {
957
- "content": "<s_bank_account_number>",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": true
963
- },
964
- "50361": {
965
- "content": "</s_due_date>",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": true
971
- },
972
- "50362": {
973
- "content": "</s_const_symbol>",
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_total_price>",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": true
995
- },
996
- "50365": {
997
- "content": "<s_const_symbol>",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": true
1003
- },
1004
- "50366": {
1005
- "content": "</s_supplier_name>",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": true
1011
- },
1012
- "50367": {
1013
- "content": "<s_total_vat>",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": true
1019
- },
1020
- "50368": {
1021
- "content": "</s_payment>",
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_issue_date>",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": true
1043
- },
1044
- "50371": {
1045
- "content": "<s_IBAN>",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": true
1051
- },
1052
- "50372": {
1053
- "content": "<s_supplier_register_id>",
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_invoice_number>",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": true
1083
- },
1084
- "50376": {
1085
- "content": "<s_supplier_tax_id>",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": true
1091
- },
1092
- "50377": {
1093
- "content": "<s_payment>",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": true
1099
- },
1100
- "50378": {
1101
- "content": "<s_customer_tax_id>",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": true
1107
- },
1108
- "50379": {
1109
- "content": "<s_invoice_number>",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": true
1115
- },
1116
- "50380": {
1117
- "content": "</s_supplier_tax_id>",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": true
1123
- },
1124
- "50381": {
1125
- "content": "<s_customer_register_id>",
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,
@@ -1137,7 +833,7 @@
1137
  "single_word": false,
1138
  "special": false
1139
  },
1140
- "50383": {
1141
  "content": "<reserved_2>",
1142
  "lstrip": false,
1143
  "normalized": true,
@@ -1145,7 +841,7 @@
1145
  "single_word": false,
1146
  "special": false
1147
  },
1148
- "50384": {
1149
  "content": "<reserved_3>",
1150
  "lstrip": false,
1151
  "normalized": true,
@@ -1153,7 +849,7 @@
1153
  "single_word": false,
1154
  "special": false
1155
  },
1156
- "50385": {
1157
  "content": "<reserved_4>",
1158
  "lstrip": false,
1159
  "normalized": true,
@@ -1161,7 +857,7 @@
1161
  "single_word": false,
1162
  "special": false
1163
  },
1164
- "50386": {
1165
  "content": "<reserved_5>",
1166
  "lstrip": false,
1167
  "normalized": true,
@@ -1169,7 +865,7 @@
1169
  "single_word": false,
1170
  "special": false
1171
  },
1172
- "50387": {
1173
  "content": "<reserved_6>",
1174
  "lstrip": false,
1175
  "normalized": true,
@@ -1177,7 +873,7 @@
1177
  "single_word": false,
1178
  "special": false
1179
  },
1180
- "50388": {
1181
  "content": "<reserved_7>",
1182
  "lstrip": false,
1183
  "normalized": true,
@@ -1185,7 +881,7 @@
1185
  "single_word": false,
1186
  "special": false
1187
  },
1188
- "50389": {
1189
  "content": "<reserved_8>",
1190
  "lstrip": false,
1191
  "normalized": true,
@@ -1193,7 +889,7 @@
1193
  "single_word": false,
1194
  "special": false
1195
  },
1196
- "50390": {
1197
  "content": "<reserved_9>",
1198
  "lstrip": false,
1199
  "normalized": true,
@@ -1201,7 +897,7 @@
1201
  "single_word": false,
1202
  "special": false
1203
  },
1204
- "50391": {
1205
  "content": "<reserved_10>",
1206
  "lstrip": false,
1207
  "normalized": true,
@@ -1209,7 +905,7 @@
1209
  "single_word": false,
1210
  "special": false
1211
  },
1212
- "50392": {
1213
  "content": "<reserved_11>",
1214
  "lstrip": false,
1215
  "normalized": true,
@@ -1217,7 +913,7 @@
1217
  "single_word": false,
1218
  "special": false
1219
  },
1220
- "50393": {
1221
  "content": "<reserved_12>",
1222
  "lstrip": false,
1223
  "normalized": true,
@@ -1225,7 +921,7 @@
1225
  "single_word": false,
1226
  "special": false
1227
  },
1228
- "50394": {
1229
  "content": "<reserved_13>",
1230
  "lstrip": false,
1231
  "normalized": true,
@@ -1233,7 +929,7 @@
1233
  "single_word": false,
1234
  "special": false
1235
  },
1236
- "50395": {
1237
  "content": "<reserved_14>",
1238
  "lstrip": false,
1239
  "normalized": true,
@@ -1241,7 +937,7 @@
1241
  "single_word": false,
1242
  "special": false
1243
  },
1244
- "50396": {
1245
  "content": "<reserved_15>",
1246
  "lstrip": false,
1247
  "normalized": true,
@@ -1249,7 +945,7 @@
1249
  "single_word": false,
1250
  "special": false
1251
  },
1252
- "50397": {
1253
  "content": "<reserved_16>",
1254
  "lstrip": false,
1255
  "normalized": true,
@@ -1257,7 +953,7 @@
1257
  "single_word": false,
1258
  "special": false
1259
  },
1260
- "50398": {
1261
  "content": "<reserved_17>",
1262
  "lstrip": false,
1263
  "normalized": true,
@@ -1265,7 +961,7 @@
1265
  "single_word": false,
1266
  "special": false
1267
  },
1268
- "50399": {
1269
  "content": "<reserved_18>",
1270
  "lstrip": false,
1271
  "normalized": true,
@@ -1273,7 +969,7 @@
1273
  "single_word": false,
1274
  "special": false
1275
  },
1276
- "50400": {
1277
  "content": "<reserved_19>",
1278
  "lstrip": false,
1279
  "normalized": true,
@@ -1281,7 +977,7 @@
1281
  "single_word": false,
1282
  "special": false
1283
  },
1284
- "50401": {
1285
  "content": "<reserved_20>",
1286
  "lstrip": false,
1287
  "normalized": true,
@@ -1289,7 +985,7 @@
1289
  "single_word": false,
1290
  "special": false
1291
  },
1292
- "50402": {
1293
  "content": "<reserved_21>",
1294
  "lstrip": false,
1295
  "normalized": true,
@@ -1297,7 +993,7 @@
1297
  "single_word": false,
1298
  "special": false
1299
  },
1300
- "50403": {
1301
  "content": "<reserved_22>",
1302
  "lstrip": false,
1303
  "normalized": true,
@@ -1305,7 +1001,7 @@
1305
  "single_word": false,
1306
  "special": false
1307
  },
1308
- "50404": {
1309
  "content": "<reserved_23>",
1310
  "lstrip": false,
1311
  "normalized": true,
@@ -1313,262 +1009,116 @@
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_BIC>",
1535
- "</s_bank_account_number>",
1536
- "<s_currency>",
1537
- "<s_customer_name>",
1538
- "<s_taxable_supply_date>",
1539
- "</s_IBAN>",
1540
- "</s_issue_date>",
1541
- "</s_customer_name>",
1542
- "</s_customer_register_id>",
1543
- "</s_currency>",
1544
- "</s_total_price>",
1545
- "<s_supplier_name>",
1546
- "</s_supplier_register_id>",
1547
- "</s_total_vat>",
1548
- "</s_taxable_supply_date>",
1549
- "</s_variable_symbol>",
1550
- "<s_bank_account_number>",
1551
- "</s_due_date>",
1552
- "</s_const_symbol>",
1553
- "<s_due_date>",
1554
- "<s_total_price>",
1555
- "<s_const_symbol>",
1556
- "</s_supplier_name>",
1557
- "<s_total_vat>",
1558
- "</s_payment>",
1559
- "<s_BIC>",
1560
- "<s_issue_date>",
1561
- "<s_IBAN>",
1562
- "<s_supplier_register_id>",
1563
- "</s_customer_tax_id>",
1564
- "<s_variable_symbol>",
1565
- "</s_invoice_number>",
1566
- "<s_supplier_tax_id>",
1567
- "<s_payment>",
1568
- "<s_customer_tax_id>",
1569
- "<s_invoice_number>",
1570
- "</s_supplier_tax_id>",
1571
- "<s_customer_register_id>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1572
  ],
1573
  "clean_up_tokenization_spaces": false,
1574
  "eos_token": "</s>",
 
826
  "special": true
827
  },
828
  "50344": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
829
  "content": "<reserved_1>",
830
  "lstrip": false,
831
  "normalized": true,
 
833
  "single_word": false,
834
  "special": false
835
  },
836
+ "50345": {
837
  "content": "<reserved_2>",
838
  "lstrip": false,
839
  "normalized": true,
 
841
  "single_word": false,
842
  "special": false
843
  },
844
+ "50346": {
845
  "content": "<reserved_3>",
846
  "lstrip": false,
847
  "normalized": true,
 
849
  "single_word": false,
850
  "special": false
851
  },
852
+ "50347": {
853
  "content": "<reserved_4>",
854
  "lstrip": false,
855
  "normalized": true,
 
857
  "single_word": false,
858
  "special": false
859
  },
860
+ "50348": {
861
  "content": "<reserved_5>",
862
  "lstrip": false,
863
  "normalized": true,
 
865
  "single_word": false,
866
  "special": false
867
  },
868
+ "50349": {
869
  "content": "<reserved_6>",
870
  "lstrip": false,
871
  "normalized": true,
 
873
  "single_word": false,
874
  "special": false
875
  },
876
+ "50350": {
877
  "content": "<reserved_7>",
878
  "lstrip": false,
879
  "normalized": true,
 
881
  "single_word": false,
882
  "special": false
883
  },
884
+ "50351": {
885
  "content": "<reserved_8>",
886
  "lstrip": false,
887
  "normalized": true,
 
889
  "single_word": false,
890
  "special": false
891
  },
892
+ "50352": {
893
  "content": "<reserved_9>",
894
  "lstrip": false,
895
  "normalized": true,
 
897
  "single_word": false,
898
  "special": false
899
  },
900
+ "50353": {
901
  "content": "<reserved_10>",
902
  "lstrip": false,
903
  "normalized": true,
 
905
  "single_word": false,
906
  "special": false
907
  },
908
+ "50354": {
909
  "content": "<reserved_11>",
910
  "lstrip": false,
911
  "normalized": true,
 
913
  "single_word": false,
914
  "special": false
915
  },
916
+ "50355": {
917
  "content": "<reserved_12>",
918
  "lstrip": false,
919
  "normalized": true,
 
921
  "single_word": false,
922
  "special": false
923
  },
924
+ "50356": {
925
  "content": "<reserved_13>",
926
  "lstrip": false,
927
  "normalized": true,
 
929
  "single_word": false,
930
  "special": false
931
  },
932
+ "50357": {
933
  "content": "<reserved_14>",
934
  "lstrip": false,
935
  "normalized": true,
 
937
  "single_word": false,
938
  "special": false
939
  },
940
+ "50358": {
941
  "content": "<reserved_15>",
942
  "lstrip": false,
943
  "normalized": true,
 
945
  "single_word": false,
946
  "special": false
947
  },
948
+ "50359": {
949
  "content": "<reserved_16>",
950
  "lstrip": false,
951
  "normalized": true,
 
953
  "single_word": false,
954
  "special": false
955
  },
956
+ "50360": {
957
  "content": "<reserved_17>",
958
  "lstrip": false,
959
  "normalized": true,
 
961
  "single_word": false,
962
  "special": false
963
  },
964
+ "50361": {
965
  "content": "<reserved_18>",
966
  "lstrip": false,
967
  "normalized": true,
 
969
  "single_word": false,
970
  "special": false
971
  },
972
+ "50362": {
973
  "content": "<reserved_19>",
974
  "lstrip": false,
975
  "normalized": true,
 
977
  "single_word": false,
978
  "special": false
979
  },
980
+ "50363": {
981
  "content": "<reserved_20>",
982
  "lstrip": false,
983
  "normalized": true,
 
985
  "single_word": false,
986
  "special": false
987
  },
988
+ "50364": {
989
  "content": "<reserved_21>",
990
  "lstrip": false,
991
  "normalized": true,
 
993
  "single_word": false,
994
  "special": false
995
  },
996
+ "50365": {
997
  "content": "<reserved_22>",
998
  "lstrip": false,
999
  "normalized": true,
 
1001
  "single_word": false,
1002
  "special": false
1003
  },
1004
+ "50366": {
1005
  "content": "<reserved_23>",
1006
  "lstrip": false,
1007
  "normalized": true,
 
1009
  "single_word": false,
1010
  "special": false
1011
  },
1012
+ "50367": {
1013
  "content": "<reserved_24>",
1014
  "lstrip": false,
1015
  "normalized": true,
1016
  "rstrip": false,
1017
  "single_word": false,
1018
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1019
  }
1020
  },
1021
  "additional_special_tokens": [
1022
+ "<extra_id_0>",
1023
+ "<extra_id_1>",
1024
+ "<extra_id_2>",
1025
+ "<extra_id_3>",
1026
+ "<extra_id_4>",
1027
+ "<extra_id_5>",
1028
+ "<extra_id_6>",
1029
+ "<extra_id_7>",
1030
+ "<extra_id_8>",
1031
+ "<extra_id_9>",
1032
+ "<extra_id_10>",
1033
+ "<extra_id_11>",
1034
+ "<extra_id_12>",
1035
+ "<extra_id_13>",
1036
+ "<extra_id_14>",
1037
+ "<extra_id_15>",
1038
+ "<extra_id_16>",
1039
+ "<extra_id_17>",
1040
+ "<extra_id_18>",
1041
+ "<extra_id_19>",
1042
+ "<extra_id_20>",
1043
+ "<extra_id_21>",
1044
+ "<extra_id_22>",
1045
+ "<extra_id_23>",
1046
+ "<extra_id_24>",
1047
+ "<extra_id_25>",
1048
+ "<extra_id_26>",
1049
+ "<extra_id_27>",
1050
+ "<extra_id_28>",
1051
+ "<extra_id_29>",
1052
+ "<extra_id_30>",
1053
+ "<extra_id_31>",
1054
+ "<extra_id_32>",
1055
+ "<extra_id_33>",
1056
+ "<extra_id_34>",
1057
+ "<extra_id_35>",
1058
+ "<extra_id_36>",
1059
+ "<extra_id_37>",
1060
+ "<extra_id_38>",
1061
+ "<extra_id_39>",
1062
+ "<extra_id_40>",
1063
+ "<extra_id_41>",
1064
+ "<extra_id_42>",
1065
+ "<extra_id_43>",
1066
+ "<extra_id_44>",
1067
+ "<extra_id_45>",
1068
+ "<extra_id_46>",
1069
+ "<extra_id_47>",
1070
+ "<extra_id_48>",
1071
+ "<extra_id_49>",
1072
+ "<extra_id_50>",
1073
+ "<extra_id_51>",
1074
+ "<extra_id_52>",
1075
+ "<extra_id_53>",
1076
+ "<extra_id_54>",
1077
+ "<extra_id_55>",
1078
+ "<extra_id_56>",
1079
+ "<extra_id_57>",
1080
+ "<extra_id_58>",
1081
+ "<extra_id_59>",
1082
+ "<extra_id_60>",
1083
+ "<extra_id_61>",
1084
+ "<extra_id_62>",
1085
+ "<extra_id_63>",
1086
+ "<extra_id_64>",
1087
+ "<extra_id_65>",
1088
+ "<extra_id_66>",
1089
+ "<extra_id_67>",
1090
+ "<extra_id_68>",
1091
+ "<extra_id_69>",
1092
+ "<extra_id_70>",
1093
+ "<extra_id_71>",
1094
+ "<extra_id_72>",
1095
+ "<extra_id_73>",
1096
+ "<extra_id_74>",
1097
+ "<extra_id_75>",
1098
+ "<extra_id_76>",
1099
+ "<extra_id_77>",
1100
+ "<extra_id_78>",
1101
+ "<extra_id_79>",
1102
+ "<extra_id_80>",
1103
+ "<extra_id_81>",
1104
+ "<extra_id_82>",
1105
+ "<extra_id_83>",
1106
+ "<extra_id_84>",
1107
+ "<extra_id_85>",
1108
+ "<extra_id_86>",
1109
+ "<extra_id_87>",
1110
+ "<extra_id_88>",
1111
+ "<extra_id_89>",
1112
+ "<extra_id_90>",
1113
+ "<extra_id_91>",
1114
+ "<extra_id_92>",
1115
+ "<extra_id_93>",
1116
+ "<extra_id_94>",
1117
+ "<extra_id_95>",
1118
+ "<extra_id_96>",
1119
+ "<extra_id_97>",
1120
+ "<extra_id_98>",
1121
+ "<extra_id_99>"
1122
  ],
1123
  "clean_up_tokenization_spaces": false,
1124
  "eos_token": "</s>",