TomasFAV commited on
Commit
c855364
·
verified ·
1 Parent(s): 7477eeb

End of training

Browse files
Files changed (4) hide show
  1. added_tokens.json +75 -11
  2. special_tokens_map.json +280 -7
  3. tokenizer.json +588 -12
  4. tokenizer_config.json +569 -18
added_tokens.json CHANGED
@@ -1,16 +1,80 @@
1
  {
2
- "</s_due_date>": 57527,
3
- "</s_invoice_number>": 57533,
4
- "</s_issue_date>": 57525,
5
- "</s_taxable_supply_date>": 57532,
6
- "<parsing>": 57526,
7
- "<reserved_1>": 57534,
8
- "<reserved_2>": 57535,
9
- "<s_due_date>": 57530,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "<s_iitcdip>": 57523,
11
- "<s_invoice_number>": 57528,
12
- "<s_issue_date>": 57529,
 
 
 
 
13
  "<s_synthdog>": 57524,
14
- "<s_taxable_supply_date>": 57531,
 
 
 
 
 
 
 
15
  "<sep/>": 57522
16
  }
 
1
  {
2
+ "</s_BIC>": 57563,
3
+ "</s_IBAN>": 57556,
4
+ "</s_bank_account_number>": 57559,
5
+ "</s_const_symbol>": 57566,
6
+ "</s_currency>": 57565,
7
+ "</s_customer_name>": 57542,
8
+ "</s_customer_register_id>": 57557,
9
+ "</s_customer_tax_id>": 57564,
10
+ "</s_due_date>": 57547,
11
+ "</s_invoice_number>": 57526,
12
+ "</s_issue_date>": 57571,
13
+ "</s_payment>": 57538,
14
+ "</s_supplier_name>": 57554,
15
+ "</s_supplier_register_id>": 57550,
16
+ "</s_supplier_tax_id>": 57530,
17
+ "</s_taxable_supply_date>": 57539,
18
+ "</s_total_price>": 57529,
19
+ "</s_total_vat>": 57549,
20
+ "</s_variable_symbol>": 57545,
21
+ "</s_vat>": 57548,
22
+ "</s_vat_base>": 57568,
23
+ "</s_vat_items>": 57533,
24
+ "</s_vat_percentage>": 57551,
25
+ "<parsing>": 57560,
26
+ "<reserved_10>": 57581,
27
+ "<reserved_11>": 57582,
28
+ "<reserved_12>": 57583,
29
+ "<reserved_13>": 57584,
30
+ "<reserved_14>": 57585,
31
+ "<reserved_15>": 57586,
32
+ "<reserved_16>": 57587,
33
+ "<reserved_17>": 57588,
34
+ "<reserved_18>": 57589,
35
+ "<reserved_19>": 57590,
36
+ "<reserved_1>": 57572,
37
+ "<reserved_20>": 57591,
38
+ "<reserved_21>": 57592,
39
+ "<reserved_22>": 57593,
40
+ "<reserved_23>": 57594,
41
+ "<reserved_24>": 57595,
42
+ "<reserved_25>": 57596,
43
+ "<reserved_26>": 57597,
44
+ "<reserved_27>": 57598,
45
+ "<reserved_28>": 57599,
46
+ "<reserved_2>": 57573,
47
+ "<reserved_3>": 57574,
48
+ "<reserved_4>": 57575,
49
+ "<reserved_5>": 57576,
50
+ "<reserved_6>": 57577,
51
+ "<reserved_7>": 57578,
52
+ "<reserved_8>": 57579,
53
+ "<reserved_9>": 57580,
54
+ "<s_BIC>": 57534,
55
+ "<s_IBAN>": 57536,
56
+ "<s_bank_account_number>": 57528,
57
+ "<s_const_symbol>": 57562,
58
+ "<s_currency>": 57531,
59
+ "<s_customer_name>": 57546,
60
+ "<s_customer_register_id>": 57570,
61
+ "<s_customer_tax_id>": 57544,
62
+ "<s_due_date>": 57525,
63
  "<s_iitcdip>": 57523,
64
+ "<s_invoice_number>": 57561,
65
+ "<s_issue_date>": 57569,
66
+ "<s_payment>": 57540,
67
+ "<s_supplier_name>": 57558,
68
+ "<s_supplier_register_id>": 57543,
69
+ "<s_supplier_tax_id>": 57552,
70
  "<s_synthdog>": 57524,
71
+ "<s_taxable_supply_date>": 57535,
72
+ "<s_total_price>": 57567,
73
+ "<s_total_vat>": 57537,
74
+ "<s_variable_symbol>": 57532,
75
+ "<s_vat>": 57527,
76
+ "<s_vat_base>": 57553,
77
+ "<s_vat_items>": 57541,
78
+ "<s_vat_percentage>": 57555,
79
  "<sep/>": 57522
80
  }
special_tokens_map.json CHANGED
@@ -1,42 +1,77 @@
1
  {
2
  "additional_special_tokens": [
3
  {
4
- "content": "</s_issue_date>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
  {
11
- "content": "<parsing>",
12
  "lstrip": false,
13
  "normalized": false,
14
  "rstrip": false,
15
  "single_word": false
16
  },
17
  {
18
- "content": "</s_due_date>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
  {
25
- "content": "<s_invoice_number>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
30
  },
31
  {
32
- "content": "<s_issue_date>",
33
  "lstrip": false,
34
  "normalized": false,
35
  "rstrip": false,
36
  "single_word": false
37
  },
38
  {
39
- "content": "<s_due_date>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  "lstrip": false,
41
  "normalized": false,
42
  "rstrip": false,
@@ -49,6 +84,27 @@
49
  "rstrip": false,
50
  "single_word": false
51
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  {
53
  "content": "</s_taxable_supply_date>",
54
  "lstrip": false,
@@ -57,7 +113,224 @@
57
  "single_word": false
58
  },
59
  {
60
- "content": "</s_invoice_number>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
  {
4
+ "content": "<s_due_date>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
  {
11
+ "content": "</s_invoice_number>",
12
  "lstrip": false,
13
  "normalized": false,
14
  "rstrip": false,
15
  "single_word": false
16
  },
17
  {
18
+ "content": "<s_vat>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
  {
25
+ "content": "<s_bank_account_number>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
30
  },
31
  {
32
+ "content": "</s_total_price>",
33
  "lstrip": false,
34
  "normalized": false,
35
  "rstrip": false,
36
  "single_word": false
37
  },
38
  {
39
+ "content": "</s_supplier_tax_id>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_currency>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<s_variable_symbol>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<sep/>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s_vat_items>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s_BIC>",
75
  "lstrip": false,
76
  "normalized": false,
77
  "rstrip": false,
 
84
  "rstrip": false,
85
  "single_word": false
86
  },
87
+ {
88
+ "content": "<s_IBAN>",
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_payment>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
  {
109
  "content": "</s_taxable_supply_date>",
110
  "lstrip": false,
 
113
  "single_word": false
114
  },
115
  {
116
+ "content": "<s_payment>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<s_vat_items>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "</s_customer_name>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<s_supplier_register_id>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s_customer_tax_id>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s_variable_symbol>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<s_customer_name>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "</s_due_date>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "</s_vat>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "</s_total_vat>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "</s_supplier_register_id>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "</s_vat_percentage>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<s_supplier_tax_id>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<s_vat_base>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "</s_supplier_name>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<s_vat_percentage>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "</s_IBAN>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "</s_customer_register_id>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<s_supplier_name>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "</s_bank_account_number>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<parsing>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<s_invoice_number>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<s_const_symbol>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "</s_BIC>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "</s_customer_tax_id>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "</s_currency>",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "</s_const_symbol>",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<s_total_price>",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "</s_vat_base>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<s_issue_date>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<s_customer_register_id>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "</s_issue_date>",
334
  "lstrip": false,
335
  "normalized": false,
336
  "rstrip": false,
tokenizer.json CHANGED
@@ -68,8 +68,8 @@
68
  "single_word": false,
69
  "lstrip": false,
70
  "rstrip": false,
71
- "normalized": true,
72
- "special": false
73
  },
74
  {
75
  "id": 57523,
@@ -91,7 +91,7 @@
91
  },
92
  {
93
  "id": 57525,
94
- "content": "</s_issue_date>",
95
  "single_word": false,
96
  "lstrip": false,
97
  "rstrip": false,
@@ -100,7 +100,7 @@
100
  },
101
  {
102
  "id": 57526,
103
- "content": "<parsing>",
104
  "single_word": false,
105
  "lstrip": false,
106
  "rstrip": false,
@@ -109,7 +109,7 @@
109
  },
110
  {
111
  "id": 57527,
112
- "content": "</s_due_date>",
113
  "single_word": false,
114
  "lstrip": false,
115
  "rstrip": false,
@@ -118,7 +118,7 @@
118
  },
119
  {
120
  "id": 57528,
121
- "content": "<s_invoice_number>",
122
  "single_word": false,
123
  "lstrip": false,
124
  "rstrip": false,
@@ -127,7 +127,7 @@
127
  },
128
  {
129
  "id": 57529,
130
- "content": "<s_issue_date>",
131
  "single_word": false,
132
  "lstrip": false,
133
  "rstrip": false,
@@ -136,7 +136,7 @@
136
  },
137
  {
138
  "id": 57530,
139
- "content": "<s_due_date>",
140
  "single_word": false,
141
  "lstrip": false,
142
  "rstrip": false,
@@ -145,7 +145,7 @@
145
  },
146
  {
147
  "id": 57531,
148
- "content": "<s_taxable_supply_date>",
149
  "single_word": false,
150
  "lstrip": false,
151
  "rstrip": false,
@@ -154,7 +154,7 @@
154
  },
155
  {
156
  "id": 57532,
157
- "content": "</s_taxable_supply_date>",
158
  "single_word": false,
159
  "lstrip": false,
160
  "rstrip": false,
@@ -163,7 +163,7 @@
163
  },
164
  {
165
  "id": 57533,
166
- "content": "</s_invoice_number>",
167
  "single_word": false,
168
  "lstrip": false,
169
  "rstrip": false,
@@ -172,6 +172,348 @@
172
  },
173
  {
174
  "id": 57534,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
  "content": "<reserved_1>",
176
  "single_word": false,
177
  "lstrip": false,
@@ -180,13 +522,247 @@
180
  "special": false
181
  },
182
  {
183
- "id": 57535,
184
  "content": "<reserved_2>",
185
  "single_word": false,
186
  "lstrip": false,
187
  "rstrip": false,
188
  "normalized": true,
189
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  }
191
  ],
192
  "normalizer": {
 
68
  "single_word": false,
69
  "lstrip": false,
70
  "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
  },
74
  {
75
  "id": 57523,
 
91
  },
92
  {
93
  "id": 57525,
94
+ "content": "<s_due_date>",
95
  "single_word": false,
96
  "lstrip": false,
97
  "rstrip": false,
 
100
  },
101
  {
102
  "id": 57526,
103
+ "content": "</s_invoice_number>",
104
  "single_word": false,
105
  "lstrip": false,
106
  "rstrip": false,
 
109
  },
110
  {
111
  "id": 57527,
112
+ "content": "<s_vat>",
113
  "single_word": false,
114
  "lstrip": false,
115
  "rstrip": false,
 
118
  },
119
  {
120
  "id": 57528,
121
+ "content": "<s_bank_account_number>",
122
  "single_word": false,
123
  "lstrip": false,
124
  "rstrip": false,
 
127
  },
128
  {
129
  "id": 57529,
130
+ "content": "</s_total_price>",
131
  "single_word": false,
132
  "lstrip": false,
133
  "rstrip": false,
 
136
  },
137
  {
138
  "id": 57530,
139
+ "content": "</s_supplier_tax_id>",
140
  "single_word": false,
141
  "lstrip": false,
142
  "rstrip": false,
 
145
  },
146
  {
147
  "id": 57531,
148
+ "content": "<s_currency>",
149
  "single_word": false,
150
  "lstrip": false,
151
  "rstrip": false,
 
154
  },
155
  {
156
  "id": 57532,
157
+ "content": "<s_variable_symbol>",
158
  "single_word": false,
159
  "lstrip": false,
160
  "rstrip": false,
 
163
  },
164
  {
165
  "id": 57533,
166
+ "content": "</s_vat_items>",
167
  "single_word": false,
168
  "lstrip": false,
169
  "rstrip": false,
 
172
  },
173
  {
174
  "id": 57534,
175
+ "content": "<s_BIC>",
176
+ "single_word": false,
177
+ "lstrip": false,
178
+ "rstrip": false,
179
+ "normalized": false,
180
+ "special": true
181
+ },
182
+ {
183
+ "id": 57535,
184
+ "content": "<s_taxable_supply_date>",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": false,
189
+ "special": true
190
+ },
191
+ {
192
+ "id": 57536,
193
+ "content": "<s_IBAN>",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": false,
198
+ "special": true
199
+ },
200
+ {
201
+ "id": 57537,
202
+ "content": "<s_total_vat>",
203
+ "single_word": false,
204
+ "lstrip": false,
205
+ "rstrip": false,
206
+ "normalized": false,
207
+ "special": true
208
+ },
209
+ {
210
+ "id": 57538,
211
+ "content": "</s_payment>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": true
217
+ },
218
+ {
219
+ "id": 57539,
220
+ "content": "</s_taxable_supply_date>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": false,
225
+ "special": true
226
+ },
227
+ {
228
+ "id": 57540,
229
+ "content": "<s_payment>",
230
+ "single_word": false,
231
+ "lstrip": false,
232
+ "rstrip": false,
233
+ "normalized": false,
234
+ "special": true
235
+ },
236
+ {
237
+ "id": 57541,
238
+ "content": "<s_vat_items>",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": true
244
+ },
245
+ {
246
+ "id": 57542,
247
+ "content": "</s_customer_name>",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": false,
252
+ "special": true
253
+ },
254
+ {
255
+ "id": 57543,
256
+ "content": "<s_supplier_register_id>",
257
+ "single_word": false,
258
+ "lstrip": false,
259
+ "rstrip": false,
260
+ "normalized": false,
261
+ "special": true
262
+ },
263
+ {
264
+ "id": 57544,
265
+ "content": "<s_customer_tax_id>",
266
+ "single_word": false,
267
+ "lstrip": false,
268
+ "rstrip": false,
269
+ "normalized": false,
270
+ "special": true
271
+ },
272
+ {
273
+ "id": 57545,
274
+ "content": "</s_variable_symbol>",
275
+ "single_word": false,
276
+ "lstrip": false,
277
+ "rstrip": false,
278
+ "normalized": false,
279
+ "special": true
280
+ },
281
+ {
282
+ "id": 57546,
283
+ "content": "<s_customer_name>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ {
291
+ "id": 57547,
292
+ "content": "</s_due_date>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": false,
297
+ "special": true
298
+ },
299
+ {
300
+ "id": 57548,
301
+ "content": "</s_vat>",
302
+ "single_word": false,
303
+ "lstrip": false,
304
+ "rstrip": false,
305
+ "normalized": false,
306
+ "special": true
307
+ },
308
+ {
309
+ "id": 57549,
310
+ "content": "</s_total_vat>",
311
+ "single_word": false,
312
+ "lstrip": false,
313
+ "rstrip": false,
314
+ "normalized": false,
315
+ "special": true
316
+ },
317
+ {
318
+ "id": 57550,
319
+ "content": "</s_supplier_register_id>",
320
+ "single_word": false,
321
+ "lstrip": false,
322
+ "rstrip": false,
323
+ "normalized": false,
324
+ "special": true
325
+ },
326
+ {
327
+ "id": 57551,
328
+ "content": "</s_vat_percentage>",
329
+ "single_word": false,
330
+ "lstrip": false,
331
+ "rstrip": false,
332
+ "normalized": false,
333
+ "special": true
334
+ },
335
+ {
336
+ "id": 57552,
337
+ "content": "<s_supplier_tax_id>",
338
+ "single_word": false,
339
+ "lstrip": false,
340
+ "rstrip": false,
341
+ "normalized": false,
342
+ "special": true
343
+ },
344
+ {
345
+ "id": 57553,
346
+ "content": "<s_vat_base>",
347
+ "single_word": false,
348
+ "lstrip": false,
349
+ "rstrip": false,
350
+ "normalized": false,
351
+ "special": true
352
+ },
353
+ {
354
+ "id": 57554,
355
+ "content": "</s_supplier_name>",
356
+ "single_word": false,
357
+ "lstrip": false,
358
+ "rstrip": false,
359
+ "normalized": false,
360
+ "special": true
361
+ },
362
+ {
363
+ "id": 57555,
364
+ "content": "<s_vat_percentage>",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": false,
369
+ "special": true
370
+ },
371
+ {
372
+ "id": 57556,
373
+ "content": "</s_IBAN>",
374
+ "single_word": false,
375
+ "lstrip": false,
376
+ "rstrip": false,
377
+ "normalized": false,
378
+ "special": true
379
+ },
380
+ {
381
+ "id": 57557,
382
+ "content": "</s_customer_register_id>",
383
+ "single_word": false,
384
+ "lstrip": false,
385
+ "rstrip": false,
386
+ "normalized": false,
387
+ "special": true
388
+ },
389
+ {
390
+ "id": 57558,
391
+ "content": "<s_supplier_name>",
392
+ "single_word": false,
393
+ "lstrip": false,
394
+ "rstrip": false,
395
+ "normalized": false,
396
+ "special": true
397
+ },
398
+ {
399
+ "id": 57559,
400
+ "content": "</s_bank_account_number>",
401
+ "single_word": false,
402
+ "lstrip": false,
403
+ "rstrip": false,
404
+ "normalized": false,
405
+ "special": true
406
+ },
407
+ {
408
+ "id": 57560,
409
+ "content": "<parsing>",
410
+ "single_word": false,
411
+ "lstrip": false,
412
+ "rstrip": false,
413
+ "normalized": false,
414
+ "special": true
415
+ },
416
+ {
417
+ "id": 57561,
418
+ "content": "<s_invoice_number>",
419
+ "single_word": false,
420
+ "lstrip": false,
421
+ "rstrip": false,
422
+ "normalized": false,
423
+ "special": true
424
+ },
425
+ {
426
+ "id": 57562,
427
+ "content": "<s_const_symbol>",
428
+ "single_word": false,
429
+ "lstrip": false,
430
+ "rstrip": false,
431
+ "normalized": false,
432
+ "special": true
433
+ },
434
+ {
435
+ "id": 57563,
436
+ "content": "</s_BIC>",
437
+ "single_word": false,
438
+ "lstrip": false,
439
+ "rstrip": false,
440
+ "normalized": false,
441
+ "special": true
442
+ },
443
+ {
444
+ "id": 57564,
445
+ "content": "</s_customer_tax_id>",
446
+ "single_word": false,
447
+ "lstrip": false,
448
+ "rstrip": false,
449
+ "normalized": false,
450
+ "special": true
451
+ },
452
+ {
453
+ "id": 57565,
454
+ "content": "</s_currency>",
455
+ "single_word": false,
456
+ "lstrip": false,
457
+ "rstrip": false,
458
+ "normalized": false,
459
+ "special": true
460
+ },
461
+ {
462
+ "id": 57566,
463
+ "content": "</s_const_symbol>",
464
+ "single_word": false,
465
+ "lstrip": false,
466
+ "rstrip": false,
467
+ "normalized": false,
468
+ "special": true
469
+ },
470
+ {
471
+ "id": 57567,
472
+ "content": "<s_total_price>",
473
+ "single_word": false,
474
+ "lstrip": false,
475
+ "rstrip": false,
476
+ "normalized": false,
477
+ "special": true
478
+ },
479
+ {
480
+ "id": 57568,
481
+ "content": "</s_vat_base>",
482
+ "single_word": false,
483
+ "lstrip": false,
484
+ "rstrip": false,
485
+ "normalized": false,
486
+ "special": true
487
+ },
488
+ {
489
+ "id": 57569,
490
+ "content": "<s_issue_date>",
491
+ "single_word": false,
492
+ "lstrip": false,
493
+ "rstrip": false,
494
+ "normalized": false,
495
+ "special": true
496
+ },
497
+ {
498
+ "id": 57570,
499
+ "content": "<s_customer_register_id>",
500
+ "single_word": false,
501
+ "lstrip": false,
502
+ "rstrip": false,
503
+ "normalized": false,
504
+ "special": true
505
+ },
506
+ {
507
+ "id": 57571,
508
+ "content": "</s_issue_date>",
509
+ "single_word": false,
510
+ "lstrip": false,
511
+ "rstrip": false,
512
+ "normalized": false,
513
+ "special": true
514
+ },
515
+ {
516
+ "id": 57572,
517
  "content": "<reserved_1>",
518
  "single_word": false,
519
  "lstrip": false,
 
522
  "special": false
523
  },
524
  {
525
+ "id": 57573,
526
  "content": "<reserved_2>",
527
  "single_word": false,
528
  "lstrip": false,
529
  "rstrip": false,
530
  "normalized": true,
531
  "special": false
532
+ },
533
+ {
534
+ "id": 57574,
535
+ "content": "<reserved_3>",
536
+ "single_word": false,
537
+ "lstrip": false,
538
+ "rstrip": false,
539
+ "normalized": true,
540
+ "special": false
541
+ },
542
+ {
543
+ "id": 57575,
544
+ "content": "<reserved_4>",
545
+ "single_word": false,
546
+ "lstrip": false,
547
+ "rstrip": false,
548
+ "normalized": true,
549
+ "special": false
550
+ },
551
+ {
552
+ "id": 57576,
553
+ "content": "<reserved_5>",
554
+ "single_word": false,
555
+ "lstrip": false,
556
+ "rstrip": false,
557
+ "normalized": true,
558
+ "special": false
559
+ },
560
+ {
561
+ "id": 57577,
562
+ "content": "<reserved_6>",
563
+ "single_word": false,
564
+ "lstrip": false,
565
+ "rstrip": false,
566
+ "normalized": true,
567
+ "special": false
568
+ },
569
+ {
570
+ "id": 57578,
571
+ "content": "<reserved_7>",
572
+ "single_word": false,
573
+ "lstrip": false,
574
+ "rstrip": false,
575
+ "normalized": true,
576
+ "special": false
577
+ },
578
+ {
579
+ "id": 57579,
580
+ "content": "<reserved_8>",
581
+ "single_word": false,
582
+ "lstrip": false,
583
+ "rstrip": false,
584
+ "normalized": true,
585
+ "special": false
586
+ },
587
+ {
588
+ "id": 57580,
589
+ "content": "<reserved_9>",
590
+ "single_word": false,
591
+ "lstrip": false,
592
+ "rstrip": false,
593
+ "normalized": true,
594
+ "special": false
595
+ },
596
+ {
597
+ "id": 57581,
598
+ "content": "<reserved_10>",
599
+ "single_word": false,
600
+ "lstrip": false,
601
+ "rstrip": false,
602
+ "normalized": true,
603
+ "special": false
604
+ },
605
+ {
606
+ "id": 57582,
607
+ "content": "<reserved_11>",
608
+ "single_word": false,
609
+ "lstrip": false,
610
+ "rstrip": false,
611
+ "normalized": true,
612
+ "special": false
613
+ },
614
+ {
615
+ "id": 57583,
616
+ "content": "<reserved_12>",
617
+ "single_word": false,
618
+ "lstrip": false,
619
+ "rstrip": false,
620
+ "normalized": true,
621
+ "special": false
622
+ },
623
+ {
624
+ "id": 57584,
625
+ "content": "<reserved_13>",
626
+ "single_word": false,
627
+ "lstrip": false,
628
+ "rstrip": false,
629
+ "normalized": true,
630
+ "special": false
631
+ },
632
+ {
633
+ "id": 57585,
634
+ "content": "<reserved_14>",
635
+ "single_word": false,
636
+ "lstrip": false,
637
+ "rstrip": false,
638
+ "normalized": true,
639
+ "special": false
640
+ },
641
+ {
642
+ "id": 57586,
643
+ "content": "<reserved_15>",
644
+ "single_word": false,
645
+ "lstrip": false,
646
+ "rstrip": false,
647
+ "normalized": true,
648
+ "special": false
649
+ },
650
+ {
651
+ "id": 57587,
652
+ "content": "<reserved_16>",
653
+ "single_word": false,
654
+ "lstrip": false,
655
+ "rstrip": false,
656
+ "normalized": true,
657
+ "special": false
658
+ },
659
+ {
660
+ "id": 57588,
661
+ "content": "<reserved_17>",
662
+ "single_word": false,
663
+ "lstrip": false,
664
+ "rstrip": false,
665
+ "normalized": true,
666
+ "special": false
667
+ },
668
+ {
669
+ "id": 57589,
670
+ "content": "<reserved_18>",
671
+ "single_word": false,
672
+ "lstrip": false,
673
+ "rstrip": false,
674
+ "normalized": true,
675
+ "special": false
676
+ },
677
+ {
678
+ "id": 57590,
679
+ "content": "<reserved_19>",
680
+ "single_word": false,
681
+ "lstrip": false,
682
+ "rstrip": false,
683
+ "normalized": true,
684
+ "special": false
685
+ },
686
+ {
687
+ "id": 57591,
688
+ "content": "<reserved_20>",
689
+ "single_word": false,
690
+ "lstrip": false,
691
+ "rstrip": false,
692
+ "normalized": true,
693
+ "special": false
694
+ },
695
+ {
696
+ "id": 57592,
697
+ "content": "<reserved_21>",
698
+ "single_word": false,
699
+ "lstrip": false,
700
+ "rstrip": false,
701
+ "normalized": true,
702
+ "special": false
703
+ },
704
+ {
705
+ "id": 57593,
706
+ "content": "<reserved_22>",
707
+ "single_word": false,
708
+ "lstrip": false,
709
+ "rstrip": false,
710
+ "normalized": true,
711
+ "special": false
712
+ },
713
+ {
714
+ "id": 57594,
715
+ "content": "<reserved_23>",
716
+ "single_word": false,
717
+ "lstrip": false,
718
+ "rstrip": false,
719
+ "normalized": true,
720
+ "special": false
721
+ },
722
+ {
723
+ "id": 57595,
724
+ "content": "<reserved_24>",
725
+ "single_word": false,
726
+ "lstrip": false,
727
+ "rstrip": false,
728
+ "normalized": true,
729
+ "special": false
730
+ },
731
+ {
732
+ "id": 57596,
733
+ "content": "<reserved_25>",
734
+ "single_word": false,
735
+ "lstrip": false,
736
+ "rstrip": false,
737
+ "normalized": true,
738
+ "special": false
739
+ },
740
+ {
741
+ "id": 57597,
742
+ "content": "<reserved_26>",
743
+ "single_word": false,
744
+ "lstrip": false,
745
+ "rstrip": false,
746
+ "normalized": true,
747
+ "special": false
748
+ },
749
+ {
750
+ "id": 57598,
751
+ "content": "<reserved_27>",
752
+ "single_word": false,
753
+ "lstrip": false,
754
+ "rstrip": false,
755
+ "normalized": true,
756
+ "special": false
757
+ },
758
+ {
759
+ "id": 57599,
760
+ "content": "<reserved_28>",
761
+ "single_word": false,
762
+ "lstrip": false,
763
+ "rstrip": false,
764
+ "normalized": true,
765
+ "special": false
766
  }
767
  ],
768
  "normalizer": {
tokenizer_config.json CHANGED
@@ -43,10 +43,10 @@
43
  "57522": {
44
  "content": "<sep/>",
45
  "lstrip": false,
46
- "normalized": true,
47
  "rstrip": false,
48
  "single_word": false,
49
- "special": false
50
  },
51
  "57523": {
52
  "content": "<s_iitcdip>",
@@ -65,7 +65,7 @@
65
  "special": true
66
  },
67
  "57525": {
68
- "content": "</s_issue_date>",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
@@ -73,7 +73,7 @@
73
  "special": true
74
  },
75
  "57526": {
76
- "content": "<parsing>",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
@@ -81,7 +81,7 @@
81
  "special": true
82
  },
83
  "57527": {
84
- "content": "</s_due_date>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
@@ -89,7 +89,7 @@
89
  "special": true
90
  },
91
  "57528": {
92
- "content": "<s_invoice_number>",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
@@ -97,7 +97,7 @@
97
  "special": true
98
  },
99
  "57529": {
100
- "content": "<s_issue_date>",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
@@ -105,7 +105,7 @@
105
  "special": true
106
  },
107
  "57530": {
108
- "content": "<s_due_date>",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  "special": true
114
  },
115
  "57531": {
116
- "content": "<s_taxable_supply_date>",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
@@ -121,7 +121,7 @@
121
  "special": true
122
  },
123
  "57532": {
124
- "content": "</s_taxable_supply_date>",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
@@ -129,7 +129,7 @@
129
  "special": true
130
  },
131
  "57533": {
132
- "content": "</s_invoice_number>",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
@@ -137,6 +137,310 @@
137
  "special": true
138
  },
139
  "57534": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  "content": "<reserved_1>",
141
  "lstrip": false,
142
  "normalized": true,
@@ -144,25 +448,272 @@
144
  "single_word": false,
145
  "special": false
146
  },
147
- "57535": {
148
  "content": "<reserved_2>",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
152
  "single_word": false,
153
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
  }
155
  },
156
  "additional_special_tokens": [
157
- "</s_issue_date>",
158
- "<parsing>",
159
- "</s_due_date>",
160
- "<s_invoice_number>",
161
- "<s_issue_date>",
162
  "<s_due_date>",
 
 
 
 
 
 
 
 
 
 
163
  "<s_taxable_supply_date>",
 
 
 
164
  "</s_taxable_supply_date>",
165
- "</s_invoice_number>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  ],
167
  "bos_token": "<s>",
168
  "clean_up_tokenization_spaces": false,
 
43
  "57522": {
44
  "content": "<sep/>",
45
  "lstrip": false,
46
+ "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
+ "special": true
50
  },
51
  "57523": {
52
  "content": "<s_iitcdip>",
 
65
  "special": true
66
  },
67
  "57525": {
68
+ "content": "<s_due_date>",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
 
73
  "special": true
74
  },
75
  "57526": {
76
+ "content": "</s_invoice_number>",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
 
81
  "special": true
82
  },
83
  "57527": {
84
+ "content": "<s_vat>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
 
89
  "special": true
90
  },
91
  "57528": {
92
+ "content": "<s_bank_account_number>",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
 
97
  "special": true
98
  },
99
  "57529": {
100
+ "content": "</s_total_price>",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
 
105
  "special": true
106
  },
107
  "57530": {
108
+ "content": "</s_supplier_tax_id>",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
 
113
  "special": true
114
  },
115
  "57531": {
116
+ "content": "<s_currency>",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
 
121
  "special": true
122
  },
123
  "57532": {
124
+ "content": "<s_variable_symbol>",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
 
129
  "special": true
130
  },
131
  "57533": {
132
+ "content": "</s_vat_items>",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
 
137
  "special": true
138
  },
139
  "57534": {
140
+ "content": "<s_BIC>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<s_taxable_supply_date>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "<s_IBAN>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_total_vat>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "</s_payment>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "</s_taxable_supply_date>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "<s_payment>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<s_vat_items>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "</s_customer_name>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<s_supplier_register_id>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "<s_customer_tax_id>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "57545": {
228
+ "content": "</s_variable_symbol>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "57546": {
236
+ "content": "<s_customer_name>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "57547": {
244
+ "content": "</s_due_date>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "57548": {
252
+ "content": "</s_vat>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57549": {
260
+ "content": "</s_total_vat>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "57550": {
268
+ "content": "</s_supplier_register_id>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "57551": {
276
+ "content": "</s_vat_percentage>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "57552": {
284
+ "content": "<s_supplier_tax_id>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "57553": {
292
+ "content": "<s_vat_base>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "57554": {
300
+ "content": "</s_supplier_name>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "57555": {
308
+ "content": "<s_vat_percentage>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "57556": {
316
+ "content": "</s_IBAN>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "57557": {
324
+ "content": "</s_customer_register_id>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "57558": {
332
+ "content": "<s_supplier_name>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "57559": {
340
+ "content": "</s_bank_account_number>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "57560": {
348
+ "content": "<parsing>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "57561": {
356
+ "content": "<s_invoice_number>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "57562": {
364
+ "content": "<s_const_symbol>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "57563": {
372
+ "content": "</s_BIC>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "57564": {
380
+ "content": "</s_customer_tax_id>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "57565": {
388
+ "content": "</s_currency>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "57566": {
396
+ "content": "</s_const_symbol>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "57567": {
404
+ "content": "<s_total_price>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "57568": {
412
+ "content": "</s_vat_base>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "57569": {
420
+ "content": "<s_issue_date>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "57570": {
428
+ "content": "<s_customer_register_id>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "57571": {
436
+ "content": "</s_issue_date>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "57572": {
444
  "content": "<reserved_1>",
445
  "lstrip": false,
446
  "normalized": true,
 
448
  "single_word": false,
449
  "special": false
450
  },
451
+ "57573": {
452
  "content": "<reserved_2>",
453
  "lstrip": false,
454
  "normalized": true,
455
  "rstrip": false,
456
  "single_word": false,
457
  "special": false
458
+ },
459
+ "57574": {
460
+ "content": "<reserved_3>",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "57575": {
468
+ "content": "<reserved_4>",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "57576": {
476
+ "content": "<reserved_5>",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "57577": {
484
+ "content": "<reserved_6>",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "57578": {
492
+ "content": "<reserved_7>",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "57579": {
500
+ "content": "<reserved_8>",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "57580": {
508
+ "content": "<reserved_9>",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "57581": {
516
+ "content": "<reserved_10>",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "57582": {
524
+ "content": "<reserved_11>",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "57583": {
532
+ "content": "<reserved_12>",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "57584": {
540
+ "content": "<reserved_13>",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "57585": {
548
+ "content": "<reserved_14>",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "57586": {
556
+ "content": "<reserved_15>",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "57587": {
564
+ "content": "<reserved_16>",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "57588": {
572
+ "content": "<reserved_17>",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "57589": {
580
+ "content": "<reserved_18>",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "57590": {
588
+ "content": "<reserved_19>",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "57591": {
596
+ "content": "<reserved_20>",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "57592": {
604
+ "content": "<reserved_21>",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "57593": {
612
+ "content": "<reserved_22>",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "57594": {
620
+ "content": "<reserved_23>",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "57595": {
628
+ "content": "<reserved_24>",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "57596": {
636
+ "content": "<reserved_25>",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "57597": {
644
+ "content": "<reserved_26>",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "57598": {
652
+ "content": "<reserved_27>",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "57599": {
660
+ "content": "<reserved_28>",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
  }
667
  },
668
  "additional_special_tokens": [
 
 
 
 
 
669
  "<s_due_date>",
670
+ "</s_invoice_number>",
671
+ "<s_vat>",
672
+ "<s_bank_account_number>",
673
+ "</s_total_price>",
674
+ "</s_supplier_tax_id>",
675
+ "<s_currency>",
676
+ "<s_variable_symbol>",
677
+ "<sep/>",
678
+ "</s_vat_items>",
679
+ "<s_BIC>",
680
  "<s_taxable_supply_date>",
681
+ "<s_IBAN>",
682
+ "<s_total_vat>",
683
+ "</s_payment>",
684
  "</s_taxable_supply_date>",
685
+ "<s_payment>",
686
+ "<s_vat_items>",
687
+ "</s_customer_name>",
688
+ "<s_supplier_register_id>",
689
+ "<s_customer_tax_id>",
690
+ "</s_variable_symbol>",
691
+ "<s_customer_name>",
692
+ "</s_due_date>",
693
+ "</s_vat>",
694
+ "</s_total_vat>",
695
+ "</s_supplier_register_id>",
696
+ "</s_vat_percentage>",
697
+ "<s_supplier_tax_id>",
698
+ "<s_vat_base>",
699
+ "</s_supplier_name>",
700
+ "<s_vat_percentage>",
701
+ "</s_IBAN>",
702
+ "</s_customer_register_id>",
703
+ "<s_supplier_name>",
704
+ "</s_bank_account_number>",
705
+ "<parsing>",
706
+ "<s_invoice_number>",
707
+ "<s_const_symbol>",
708
+ "</s_BIC>",
709
+ "</s_customer_tax_id>",
710
+ "</s_currency>",
711
+ "</s_const_symbol>",
712
+ "<s_total_price>",
713
+ "</s_vat_base>",
714
+ "<s_issue_date>",
715
+ "<s_customer_register_id>",
716
+ "</s_issue_date>"
717
  ],
718
  "bos_token": "<s>",
719
  "clean_up_tokenization_spaces": false,