waceke commited on
Commit
1813686
·
verified ·
1 Parent(s): dfa73f4

Training done

Browse files
Files changed (3) hide show
  1. added_tokens.json +39 -51
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +39 -142
added_tokens.json CHANGED
@@ -1,58 +1,46 @@
1
  {
2
- "</s_bar_code>": 57551,
3
- "</s_box_no>": 57546,
4
- "</s_family>": 57567,
5
- "</s_item>": 57559,
6
- "</s_item_barcode>": 57561,
7
- "</s_item_batch>": 57548,
8
- "</s_item_code>": 57532,
9
- "</s_item_decsription>": 57571,
10
- "</s_item_description>": 57528,
11
- "</s_item_quantity>": 57530,
12
- "</s_item_quantity_billed>": 57540,
13
- "</s_item_quantity_ordered>": 57553,
14
- "</s_item_quantity_received>": 57557,
15
- "</s_item_quantity_rejected>": 57573,
16
- "</s_item_quantity_scanned>": 57555,
17
- "</s_item_quantity_shipped>": 57538,
18
- "</s_item_quantity_short>": 57569,
19
- "</s_item_total_price>": 57544,
20
- "</s_item_total_quantity>": 57577,
21
- "</s_item_unit>": 57563,
22
- "</s_item_unit_price>": 57542,
23
- "</s_item_unit_quantity>": 57575,
24
- "</s_item_uom>": 57534,
25
- "</s_item_weight>": 57536,
26
  "</s_items>": 57526,
27
- "</s_supplier_reference>": 57565,
28
- "<s_bar_code>": 57550,
29
- "<s_box_no>": 57545,
30
- "<s_cord-v2>": 57549,
31
- "<s_family>": 57566,
32
  "<s_iitcdip>": 57523,
33
- "<s_item>": 57558,
34
- "<s_item_barcode>": 57560,
35
- "<s_item_batch>": 57547,
36
- "<s_item_code>": 57531,
37
- "<s_item_decsription>": 57570,
38
- "<s_item_description>": 57527,
39
- "<s_item_quantity>": 57529,
40
- "<s_item_quantity_billed>": 57539,
41
- "<s_item_quantity_ordered>": 57552,
42
- "<s_item_quantity_received>": 57556,
43
- "<s_item_quantity_rejected>": 57572,
44
- "<s_item_quantity_scanned>": 57554,
45
- "<s_item_quantity_shipped>": 57537,
46
- "<s_item_quantity_short>": 57568,
47
- "<s_item_total_price>": 57543,
48
- "<s_item_total_quantity>": 57576,
49
- "<s_item_unit>": 57562,
50
- "<s_item_unit_price>": 57541,
51
- "<s_item_unit_quantity>": 57574,
52
- "<s_item_uom>": 57533,
53
- "<s_item_weight>": 57535,
54
  "<s_items>": 57525,
55
- "<s_supplier_reference>": 57564,
56
  "<s_synthdog>": 57524,
57
  "<sep/>": 57522
58
  }
 
1
  {
2
+ "</s_box_no>": 57536,
3
+ "</s_family>": 57538,
4
+ "</s_item_barcode>": 57540,
5
+ "</s_item_batch>": 57542,
6
+ "</s_item_code>": 57528,
7
+ "</s_item_description>": 57530,
8
+ "</s_item_quantity>": 57532,
9
+ "</s_item_quantity_billed>": 57544,
10
+ "</s_item_quantity_ordered>": 57546,
11
+ "</s_item_quantity_received>": 57548,
12
+ "</s_item_quantity_rejected>": 57550,
13
+ "</s_item_quantity_scanned>": 57552,
14
+ "</s_item_quantity_shipped>": 57554,
15
+ "</s_item_quantity_short>": 57556,
16
+ "</s_item_total_price>": 57558,
17
+ "</s_item_total_quantity>": 57560,
18
+ "</s_item_unit_price>": 57562,
19
+ "</s_item_unit_quantity>": 57534,
20
+ "</s_item_weight>": 57564,
 
 
 
 
 
21
  "</s_items>": 57526,
22
+ "<s_box_no>": 57535,
23
+ "<s_cord-v2>": 57565,
24
+ "<s_family>": 57537,
 
 
25
  "<s_iitcdip>": 57523,
26
+ "<s_item_barcode>": 57539,
27
+ "<s_item_batch>": 57541,
28
+ "<s_item_code>": 57527,
29
+ "<s_item_description>": 57529,
30
+ "<s_item_quantity>": 57531,
31
+ "<s_item_quantity_billed>": 57543,
32
+ "<s_item_quantity_ordered>": 57545,
33
+ "<s_item_quantity_received>": 57547,
34
+ "<s_item_quantity_rejected>": 57549,
35
+ "<s_item_quantity_scanned>": 57551,
36
+ "<s_item_quantity_shipped>": 57553,
37
+ "<s_item_quantity_short>": 57555,
38
+ "<s_item_total_price>": 57557,
39
+ "<s_item_total_quantity>": 57559,
40
+ "<s_item_unit_price>": 57561,
41
+ "<s_item_unit_quantity>": 57533,
42
+ "<s_item_weight>": 57563,
 
 
 
 
43
  "<s_items>": 57525,
 
44
  "<s_synthdog>": 57524,
45
  "<sep/>": 57522
46
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -81,7 +81,7 @@
81
  "special": false
82
  },
83
  "57527": {
84
- "content": "<s_item_description>",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
@@ -89,7 +89,7 @@
89
  "special": false
90
  },
91
  "57528": {
92
- "content": "</s_item_description>",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
@@ -97,7 +97,7 @@
97
  "special": false
98
  },
99
  "57529": {
100
- "content": "<s_item_quantity>",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
@@ -105,7 +105,7 @@
105
  "special": false
106
  },
107
  "57530": {
108
- "content": "</s_item_quantity>",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  "special": false
114
  },
115
  "57531": {
116
- "content": "<s_item_code>",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
@@ -121,7 +121,7 @@
121
  "special": false
122
  },
123
  "57532": {
124
- "content": "</s_item_code>",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
@@ -129,7 +129,7 @@
129
  "special": false
130
  },
131
  "57533": {
132
- "content": "<s_item_uom>",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
@@ -137,7 +137,7 @@
137
  "special": false
138
  },
139
  "57534": {
140
- "content": "</s_item_uom>",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
@@ -145,7 +145,7 @@
145
  "special": false
146
  },
147
  "57535": {
148
- "content": "<s_item_weight>",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
@@ -153,7 +153,7 @@
153
  "special": false
154
  },
155
  "57536": {
156
- "content": "</s_item_weight>",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
@@ -161,7 +161,7 @@
161
  "special": false
162
  },
163
  "57537": {
164
- "content": "<s_item_quantity_shipped>",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
@@ -169,7 +169,7 @@
169
  "special": false
170
  },
171
  "57538": {
172
- "content": "</s_item_quantity_shipped>",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
@@ -177,7 +177,7 @@
177
  "special": false
178
  },
179
  "57539": {
180
- "content": "<s_item_quantity_billed>",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  "special": false
186
  },
187
  "57540": {
188
- "content": "</s_item_quantity_billed>",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
@@ -193,7 +193,7 @@
193
  "special": false
194
  },
195
  "57541": {
196
- "content": "<s_item_unit_price>",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
@@ -201,7 +201,7 @@
201
  "special": false
202
  },
203
  "57542": {
204
- "content": "</s_item_unit_price>",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
@@ -209,7 +209,7 @@
209
  "special": false
210
  },
211
  "57543": {
212
- "content": "<s_item_total_price>",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
@@ -217,7 +217,7 @@
217
  "special": false
218
  },
219
  "57544": {
220
- "content": "</s_item_total_price>",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
@@ -225,7 +225,7 @@
225
  "special": false
226
  },
227
  "57545": {
228
- "content": "<s_box_no>",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
@@ -233,7 +233,7 @@
233
  "special": false
234
  },
235
  "57546": {
236
- "content": "</s_box_no>",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
@@ -241,7 +241,7 @@
241
  "special": false
242
  },
243
  "57547": {
244
- "content": "<s_item_batch>",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
@@ -249,7 +249,7 @@
249
  "special": false
250
  },
251
  "57548": {
252
- "content": "</s_item_batch>",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  "special": false
258
  },
259
  "57549": {
260
- "content": "<s_cord-v2>",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
@@ -265,7 +265,7 @@
265
  "special": false
266
  },
267
  "57550": {
268
- "content": "<s_bar_code>",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
@@ -273,7 +273,7 @@
273
  "special": false
274
  },
275
  "57551": {
276
- "content": "</s_bar_code>",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
@@ -281,7 +281,7 @@
281
  "special": false
282
  },
283
  "57552": {
284
- "content": "<s_item_quantity_ordered>",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
@@ -289,7 +289,7 @@
289
  "special": false
290
  },
291
  "57553": {
292
- "content": "</s_item_quantity_ordered>",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
@@ -297,7 +297,7 @@
297
  "special": false
298
  },
299
  "57554": {
300
- "content": "<s_item_quantity_scanned>",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
@@ -305,7 +305,7 @@
305
  "special": false
306
  },
307
  "57555": {
308
- "content": "</s_item_quantity_scanned>",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
@@ -313,7 +313,7 @@
313
  "special": false
314
  },
315
  "57556": {
316
- "content": "<s_item_quantity_received>",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
@@ -321,7 +321,7 @@
321
  "special": false
322
  },
323
  "57557": {
324
- "content": "</s_item_quantity_received>",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  "special": false
330
  },
331
  "57558": {
332
- "content": "<s_item>",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
@@ -337,7 +337,7 @@
337
  "special": false
338
  },
339
  "57559": {
340
- "content": "</s_item>",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
@@ -345,7 +345,7 @@
345
  "special": false
346
  },
347
  "57560": {
348
- "content": "<s_item_barcode>",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
@@ -353,7 +353,7 @@
353
  "special": false
354
  },
355
  "57561": {
356
- "content": "</s_item_barcode>",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
@@ -361,7 +361,7 @@
361
  "special": false
362
  },
363
  "57562": {
364
- "content": "<s_item_unit>",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
@@ -369,7 +369,7 @@
369
  "special": false
370
  },
371
  "57563": {
372
- "content": "</s_item_unit>",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
@@ -377,7 +377,7 @@
377
  "special": false
378
  },
379
  "57564": {
380
- "content": "<s_supplier_reference>",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
@@ -385,103 +385,7 @@
385
  "special": false
386
  },
387
  "57565": {
388
- "content": "</s_supplier_reference>",
389
- "lstrip": false,
390
- "normalized": true,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "57566": {
396
- "content": "<s_family>",
397
- "lstrip": false,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "57567": {
404
- "content": "</s_family>",
405
- "lstrip": false,
406
- "normalized": true,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "57568": {
412
- "content": "<s_item_quantity_short>",
413
- "lstrip": false,
414
- "normalized": true,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "57569": {
420
- "content": "</s_item_quantity_short>",
421
- "lstrip": false,
422
- "normalized": true,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "57570": {
428
- "content": "<s_item_decsription>",
429
- "lstrip": false,
430
- "normalized": true,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "57571": {
436
- "content": "</s_item_decsription>",
437
- "lstrip": false,
438
- "normalized": true,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "57572": {
444
- "content": "<s_item_quantity_rejected>",
445
- "lstrip": false,
446
- "normalized": true,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "57573": {
452
- "content": "</s_item_quantity_rejected>",
453
- "lstrip": false,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "57574": {
460
- "content": "<s_item_unit_quantity>",
461
- "lstrip": false,
462
- "normalized": true,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "57575": {
468
- "content": "</s_item_unit_quantity>",
469
- "lstrip": false,
470
- "normalized": true,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "57576": {
476
- "content": "<s_item_total_quantity>",
477
- "lstrip": false,
478
- "normalized": true,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "57577": {
484
- "content": "</s_item_total_quantity>",
485
  "lstrip": false,
486
  "normalized": true,
487
  "rstrip": false,
@@ -498,18 +402,11 @@
498
  "cls_token": "<s>",
499
  "eos_token": "</s>",
500
  "mask_token": "<mask>",
501
- "max_length": 768,
502
  "model_max_length": 1000000000000000019884624838656,
503
- "pad_to_multiple_of": null,
504
  "pad_token": "<pad>",
505
- "pad_token_type_id": 0,
506
- "padding_side": "right",
507
  "processor_class": "DonutProcessor",
508
  "sep_token": "</s>",
509
  "sp_model_kwargs": {},
510
- "stride": 0,
511
  "tokenizer_class": "XLMRobertaTokenizer",
512
- "truncation_side": "right",
513
- "truncation_strategy": "longest_first",
514
  "unk_token": "<unk>"
515
  }
 
81
  "special": false
82
  },
83
  "57527": {
84
+ "content": "<s_item_code>",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
 
89
  "special": false
90
  },
91
  "57528": {
92
+ "content": "</s_item_code>",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
 
97
  "special": false
98
  },
99
  "57529": {
100
+ "content": "<s_item_description>",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
 
105
  "special": false
106
  },
107
  "57530": {
108
+ "content": "</s_item_description>",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
 
113
  "special": false
114
  },
115
  "57531": {
116
+ "content": "<s_item_quantity>",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
 
121
  "special": false
122
  },
123
  "57532": {
124
+ "content": "</s_item_quantity>",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
 
129
  "special": false
130
  },
131
  "57533": {
132
+ "content": "<s_item_unit_quantity>",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
 
137
  "special": false
138
  },
139
  "57534": {
140
+ "content": "</s_item_unit_quantity>",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
 
145
  "special": false
146
  },
147
  "57535": {
148
+ "content": "<s_box_no>",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
 
153
  "special": false
154
  },
155
  "57536": {
156
+ "content": "</s_box_no>",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
 
161
  "special": false
162
  },
163
  "57537": {
164
+ "content": "<s_family>",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
 
169
  "special": false
170
  },
171
  "57538": {
172
+ "content": "</s_family>",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
 
177
  "special": false
178
  },
179
  "57539": {
180
+ "content": "<s_item_barcode>",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
 
185
  "special": false
186
  },
187
  "57540": {
188
+ "content": "</s_item_barcode>",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
 
193
  "special": false
194
  },
195
  "57541": {
196
+ "content": "<s_item_batch>",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
 
201
  "special": false
202
  },
203
  "57542": {
204
+ "content": "</s_item_batch>",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
 
209
  "special": false
210
  },
211
  "57543": {
212
+ "content": "<s_item_quantity_billed>",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
 
217
  "special": false
218
  },
219
  "57544": {
220
+ "content": "</s_item_quantity_billed>",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
 
225
  "special": false
226
  },
227
  "57545": {
228
+ "content": "<s_item_quantity_ordered>",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
 
233
  "special": false
234
  },
235
  "57546": {
236
+ "content": "</s_item_quantity_ordered>",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
 
241
  "special": false
242
  },
243
  "57547": {
244
+ "content": "<s_item_quantity_received>",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
 
249
  "special": false
250
  },
251
  "57548": {
252
+ "content": "</s_item_quantity_received>",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
 
257
  "special": false
258
  },
259
  "57549": {
260
+ "content": "<s_item_quantity_rejected>",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
 
265
  "special": false
266
  },
267
  "57550": {
268
+ "content": "</s_item_quantity_rejected>",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
 
273
  "special": false
274
  },
275
  "57551": {
276
+ "content": "<s_item_quantity_scanned>",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
 
281
  "special": false
282
  },
283
  "57552": {
284
+ "content": "</s_item_quantity_scanned>",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
 
289
  "special": false
290
  },
291
  "57553": {
292
+ "content": "<s_item_quantity_shipped>",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
 
297
  "special": false
298
  },
299
  "57554": {
300
+ "content": "</s_item_quantity_shipped>",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
 
305
  "special": false
306
  },
307
  "57555": {
308
+ "content": "<s_item_quantity_short>",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
 
313
  "special": false
314
  },
315
  "57556": {
316
+ "content": "</s_item_quantity_short>",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
 
321
  "special": false
322
  },
323
  "57557": {
324
+ "content": "<s_item_total_price>",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
 
329
  "special": false
330
  },
331
  "57558": {
332
+ "content": "</s_item_total_price>",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
 
337
  "special": false
338
  },
339
  "57559": {
340
+ "content": "<s_item_total_quantity>",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
 
345
  "special": false
346
  },
347
  "57560": {
348
+ "content": "</s_item_total_quantity>",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
 
353
  "special": false
354
  },
355
  "57561": {
356
+ "content": "<s_item_unit_price>",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
 
361
  "special": false
362
  },
363
  "57562": {
364
+ "content": "</s_item_unit_price>",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
 
369
  "special": false
370
  },
371
  "57563": {
372
+ "content": "<s_item_weight>",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
 
377
  "special": false
378
  },
379
  "57564": {
380
+ "content": "</s_item_weight>",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
 
385
  "special": false
386
  },
387
  "57565": {
388
+ "content": "<s_cord-v2>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
 
402
  "cls_token": "<s>",
403
  "eos_token": "</s>",
404
  "mask_token": "<mask>",
 
405
  "model_max_length": 1000000000000000019884624838656,
 
406
  "pad_token": "<pad>",
 
 
407
  "processor_class": "DonutProcessor",
408
  "sep_token": "</s>",
409
  "sp_model_kwargs": {},
 
410
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
411
  "unk_token": "<unk>"
412
  }