MarkGG commited on
Commit
930c1ec
·
1 Parent(s): 8b9dac2

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +206 -104
  2. special_tokens_map.json +0 -1
  3. tokenizer.json +1232 -319
  4. tokenizer_config.json +1 -1
added_tokens.json CHANGED
@@ -1,106 +1,208 @@
1
  {
2
- "[ex0]": 31972,
3
- "[ex10]": 31982,
4
- "[ex11]": 31983,
5
- "[ex12]": 31984,
6
- "[ex13]": 31985,
7
- "[ex14]": 31986,
8
- "[ex15]": 31987,
9
- "[ex16]": 31988,
10
- "[ex17]": 31989,
11
- "[ex18]": 31990,
12
- "[ex19]": 31991,
13
- "[ex1]": 31973,
14
- "[ex20]": 31992,
15
- "[ex21]": 31993,
16
- "[ex22]": 31994,
17
- "[ex23]": 31995,
18
- "[ex24]": 31996,
19
- "[ex25]": 31997,
20
- "[ex26]": 31998,
21
- "[ex27]": 31999,
22
- "[ex28]": 32000,
23
- "[ex29]": 32001,
24
- "[ex2]": 31974,
25
- "[ex30]": 32002,
26
- "[ex31]": 32003,
27
- "[ex32]": 32004,
28
- "[ex33]": 32005,
29
- "[ex34]": 32006,
30
- "[ex35]": 32007,
31
- "[ex36]": 32008,
32
- "[ex37]": 32009,
33
- "[ex38]": 32010,
34
- "[ex39]": 32011,
35
- "[ex3]": 31975,
36
- "[ex40]": 32012,
37
- "[ex41]": 32013,
38
- "[ex42]": 32014,
39
- "[ex43]": 32015,
40
- "[ex44]": 32016,
41
- "[ex45]": 32017,
42
- "[ex46]": 32018,
43
- "[ex47]": 32019,
44
- "[ex48]": 32020,
45
- "[ex49]": 32021,
46
- "[ex4]": 31976,
47
- "[ex50]": 32022,
48
- "[ex51]": 32023,
49
- "[ex52]": 32024,
50
- "[ex53]": 32025,
51
- "[ex54]": 32026,
52
- "[ex55]": 32027,
53
- "[ex56]": 32028,
54
- "[ex57]": 32029,
55
- "[ex58]": 32030,
56
- "[ex59]": 32031,
57
- "[ex5]": 31977,
58
- "[ex60]": 32032,
59
- "[ex61]": 32033,
60
- "[ex62]": 32034,
61
- "[ex63]": 32035,
62
- "[ex64]": 32036,
63
- "[ex65]": 32037,
64
- "[ex66]": 32038,
65
- "[ex67]": 32039,
66
- "[ex68]": 32040,
67
- "[ex69]": 32041,
68
- "[ex6]": 31978,
69
- "[ex70]": 32042,
70
- "[ex71]": 32043,
71
- "[ex72]": 32044,
72
- "[ex73]": 32045,
73
- "[ex74]": 32046,
74
- "[ex75]": 32047,
75
- "[ex76]": 32048,
76
- "[ex77]": 32049,
77
- "[ex78]": 32050,
78
- "[ex79]": 32051,
79
- "[ex7]": 31979,
80
- "[ex80]": 32052,
81
- "[ex81]": 32053,
82
- "[ex82]": 32054,
83
- "[ex83]": 32055,
84
- "[ex84]": 32056,
85
- "[ex85]": 32057,
86
- "[ex86]": 32058,
87
- "[ex87]": 32059,
88
- "[ex88]": 32060,
89
- "[ex89]": 32061,
90
- "[ex8]": 31980,
91
- "[ex90]": 32062,
92
- "[ex91]": 32063,
93
- "[ex92]": 32064,
94
- "[ex93]": 32065,
95
- "[ex94]": 32066,
96
- "[ex95]": 32067,
97
- "[ex96]": 32068,
98
- "[ex97]": 32069,
99
- "[ex98]": 32070,
100
- "[ex99]": 32071,
101
- "[ex9]": 31981,
102
- "[frl]": 31970,
103
- "[mrl]": 31971,
104
- "ext.": 32072,
105
- "int.": 32073
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  }
 
1
  {
2
+ "[ex0]": 31974,
3
+ "[ex0]:": 32076,
4
+ "[ex10]": 31984,
5
+ "[ex10]:": 32086,
6
+ "[ex11]": 31985,
7
+ "[ex11]:": 32087,
8
+ "[ex12]": 31986,
9
+ "[ex12]:": 32088,
10
+ "[ex13]": 31987,
11
+ "[ex13]:": 32089,
12
+ "[ex14]": 31988,
13
+ "[ex14]:": 32090,
14
+ "[ex15]": 31989,
15
+ "[ex15]:": 32091,
16
+ "[ex16]": 31990,
17
+ "[ex16]:": 32092,
18
+ "[ex17]": 31991,
19
+ "[ex17]:": 32093,
20
+ "[ex18]": 31992,
21
+ "[ex18]:": 32094,
22
+ "[ex19]": 31993,
23
+ "[ex19]:": 32095,
24
+ "[ex1]": 31975,
25
+ "[ex1]:": 32077,
26
+ "[ex20]": 31994,
27
+ "[ex20]:": 32096,
28
+ "[ex21]": 31995,
29
+ "[ex21]:": 32097,
30
+ "[ex22]": 31996,
31
+ "[ex22]:": 32098,
32
+ "[ex23]": 31997,
33
+ "[ex23]:": 32099,
34
+ "[ex24]": 31998,
35
+ "[ex24]:": 32100,
36
+ "[ex25]": 31999,
37
+ "[ex25]:": 32101,
38
+ "[ex26]": 32000,
39
+ "[ex26]:": 32102,
40
+ "[ex27]": 32001,
41
+ "[ex27]:": 32103,
42
+ "[ex28]": 32002,
43
+ "[ex28]:": 32104,
44
+ "[ex29]": 32003,
45
+ "[ex29]:": 32105,
46
+ "[ex2]": 31976,
47
+ "[ex2]:": 32078,
48
+ "[ex30]": 32004,
49
+ "[ex30]:": 32106,
50
+ "[ex31]": 32005,
51
+ "[ex31]:": 32107,
52
+ "[ex32]": 32006,
53
+ "[ex32]:": 32108,
54
+ "[ex33]": 32007,
55
+ "[ex33]:": 32109,
56
+ "[ex34]": 32008,
57
+ "[ex34]:": 32110,
58
+ "[ex35]": 32009,
59
+ "[ex35]:": 32111,
60
+ "[ex36]": 32010,
61
+ "[ex36]:": 32112,
62
+ "[ex37]": 32011,
63
+ "[ex37]:": 32113,
64
+ "[ex38]": 32012,
65
+ "[ex38]:": 32114,
66
+ "[ex39]": 32013,
67
+ "[ex39]:": 32115,
68
+ "[ex3]": 31977,
69
+ "[ex3]:": 32079,
70
+ "[ex40]": 32014,
71
+ "[ex40]:": 32116,
72
+ "[ex41]": 32015,
73
+ "[ex41]:": 32117,
74
+ "[ex42]": 32016,
75
+ "[ex42]:": 32118,
76
+ "[ex43]": 32017,
77
+ "[ex43]:": 32119,
78
+ "[ex44]": 32018,
79
+ "[ex44]:": 32120,
80
+ "[ex45]": 32019,
81
+ "[ex45]:": 32121,
82
+ "[ex46]": 32020,
83
+ "[ex46]:": 32122,
84
+ "[ex47]": 32021,
85
+ "[ex47]:": 32123,
86
+ "[ex48]": 32022,
87
+ "[ex48]:": 32124,
88
+ "[ex49]": 32023,
89
+ "[ex49]:": 32125,
90
+ "[ex4]": 31978,
91
+ "[ex4]:": 32080,
92
+ "[ex50]": 32024,
93
+ "[ex50]:": 32126,
94
+ "[ex51]": 32025,
95
+ "[ex51]:": 32127,
96
+ "[ex52]": 32026,
97
+ "[ex52]:": 32128,
98
+ "[ex53]": 32027,
99
+ "[ex53]:": 32129,
100
+ "[ex54]": 32028,
101
+ "[ex54]:": 32130,
102
+ "[ex55]": 32029,
103
+ "[ex55]:": 32131,
104
+ "[ex56]": 32030,
105
+ "[ex56]:": 32132,
106
+ "[ex57]": 32031,
107
+ "[ex57]:": 32133,
108
+ "[ex58]": 32032,
109
+ "[ex58]:": 32134,
110
+ "[ex59]": 32033,
111
+ "[ex59]:": 32135,
112
+ "[ex5]": 31979,
113
+ "[ex5]:": 32081,
114
+ "[ex60]": 32034,
115
+ "[ex60]:": 32136,
116
+ "[ex61]": 32035,
117
+ "[ex61]:": 32137,
118
+ "[ex62]": 32036,
119
+ "[ex62]:": 32138,
120
+ "[ex63]": 32037,
121
+ "[ex63]:": 32139,
122
+ "[ex64]": 32038,
123
+ "[ex64]:": 32140,
124
+ "[ex65]": 32039,
125
+ "[ex65]:": 32141,
126
+ "[ex66]": 32040,
127
+ "[ex66]:": 32142,
128
+ "[ex67]": 32041,
129
+ "[ex67]:": 32143,
130
+ "[ex68]": 32042,
131
+ "[ex68]:": 32144,
132
+ "[ex69]": 32043,
133
+ "[ex69]:": 32145,
134
+ "[ex6]": 31980,
135
+ "[ex6]:": 32082,
136
+ "[ex70]": 32044,
137
+ "[ex70]:": 32146,
138
+ "[ex71]": 32045,
139
+ "[ex71]:": 32147,
140
+ "[ex72]": 32046,
141
+ "[ex72]:": 32148,
142
+ "[ex73]": 32047,
143
+ "[ex73]:": 32149,
144
+ "[ex74]": 32048,
145
+ "[ex74]:": 32150,
146
+ "[ex75]": 32049,
147
+ "[ex75]:": 32151,
148
+ "[ex76]": 32050,
149
+ "[ex76]:": 32152,
150
+ "[ex77]": 32051,
151
+ "[ex77]:": 32153,
152
+ "[ex78]": 32052,
153
+ "[ex78]:": 32154,
154
+ "[ex79]": 32053,
155
+ "[ex79]:": 32155,
156
+ "[ex7]": 31981,
157
+ "[ex7]:": 32083,
158
+ "[ex80]": 32054,
159
+ "[ex80]:": 32156,
160
+ "[ex81]": 32055,
161
+ "[ex81]:": 32157,
162
+ "[ex82]": 32056,
163
+ "[ex82]:": 32158,
164
+ "[ex83]": 32057,
165
+ "[ex83]:": 32159,
166
+ "[ex84]": 32058,
167
+ "[ex84]:": 32160,
168
+ "[ex85]": 32059,
169
+ "[ex85]:": 32161,
170
+ "[ex86]": 32060,
171
+ "[ex86]:": 32162,
172
+ "[ex87]": 32061,
173
+ "[ex87]:": 32163,
174
+ "[ex88]": 32062,
175
+ "[ex88]:": 32164,
176
+ "[ex89]": 32063,
177
+ "[ex89]:": 32165,
178
+ "[ex8]": 31982,
179
+ "[ex8]:": 32084,
180
+ "[ex90]": 32064,
181
+ "[ex90]:": 32166,
182
+ "[ex91]": 32065,
183
+ "[ex91]:": 32167,
184
+ "[ex92]": 32066,
185
+ "[ex92]:": 32168,
186
+ "[ex93]": 32067,
187
+ "[ex93]:": 32169,
188
+ "[ex94]": 32068,
189
+ "[ex94]:": 32170,
190
+ "[ex95]": 32069,
191
+ "[ex95]:": 32171,
192
+ "[ex96]": 32070,
193
+ "[ex96]:": 32172,
194
+ "[ex97]": 32071,
195
+ "[ex97]:": 32173,
196
+ "[ex98]": 32072,
197
+ "[ex98]:": 32174,
198
+ "[ex99]": 32073,
199
+ "[ex99]:": 32175,
200
+ "[ex9]": 31983,
201
+ "[ex9]:": 32085,
202
+ "[frl]": 31972,
203
+ "[frl]:": 32074,
204
+ "[mrl]": 31973,
205
+ "[mrl]:": 32075,
206
+ "ext.": 31970,
207
+ "int.": 31971
208
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
  "unk_token": "<|endoftext|>"
6
  }
 
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
 
4
  "unk_token": "<|endoftext|>"
5
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 128,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
@@ -19,939 +14,1857 @@
19
  },
20
  {
21
  "id": 31970,
22
- "content": "[frl]",
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": true,
27
- "special": false
28
  },
29
  {
30
  "id": 31971,
31
- "content": "[mrl]",
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": true,
36
- "special": false
37
  },
38
  {
39
  "id": 31972,
40
- "content": "[ex0]",
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
- "normalized": true,
45
- "special": false
46
  },
47
  {
48
  "id": 31973,
49
- "content": "[ex1]",
50
  "single_word": false,
51
  "lstrip": false,
52
  "rstrip": false,
53
- "normalized": true,
54
- "special": false
55
  },
56
  {
57
  "id": 31974,
58
- "content": "[ex2]",
59
  "single_word": false,
60
  "lstrip": false,
61
  "rstrip": false,
62
- "normalized": true,
63
- "special": false
64
  },
65
  {
66
  "id": 31975,
67
- "content": "[ex3]",
68
  "single_word": false,
69
  "lstrip": false,
70
  "rstrip": false,
71
- "normalized": true,
72
- "special": false
73
  },
74
  {
75
  "id": 31976,
76
- "content": "[ex4]",
77
  "single_word": false,
78
  "lstrip": false,
79
  "rstrip": false,
80
- "normalized": true,
81
- "special": false
82
  },
83
  {
84
  "id": 31977,
85
- "content": "[ex5]",
86
  "single_word": false,
87
  "lstrip": false,
88
  "rstrip": false,
89
- "normalized": true,
90
- "special": false
91
  },
92
  {
93
  "id": 31978,
94
- "content": "[ex6]",
95
  "single_word": false,
96
  "lstrip": false,
97
  "rstrip": false,
98
- "normalized": true,
99
- "special": false
100
  },
101
  {
102
  "id": 31979,
103
- "content": "[ex7]",
104
  "single_word": false,
105
  "lstrip": false,
106
  "rstrip": false,
107
- "normalized": true,
108
- "special": false
109
  },
110
  {
111
  "id": 31980,
112
- "content": "[ex8]",
113
  "single_word": false,
114
  "lstrip": false,
115
  "rstrip": false,
116
- "normalized": true,
117
- "special": false
118
  },
119
  {
120
  "id": 31981,
121
- "content": "[ex9]",
122
  "single_word": false,
123
  "lstrip": false,
124
  "rstrip": false,
125
- "normalized": true,
126
- "special": false
127
  },
128
  {
129
  "id": 31982,
130
- "content": "[ex10]",
131
  "single_word": false,
132
  "lstrip": false,
133
  "rstrip": false,
134
- "normalized": true,
135
- "special": false
136
  },
137
  {
138
  "id": 31983,
139
- "content": "[ex11]",
140
  "single_word": false,
141
  "lstrip": false,
142
  "rstrip": false,
143
- "normalized": true,
144
- "special": false
145
  },
146
  {
147
  "id": 31984,
148
- "content": "[ex12]",
149
  "single_word": false,
150
  "lstrip": false,
151
  "rstrip": false,
152
- "normalized": true,
153
- "special": false
154
  },
155
  {
156
  "id": 31985,
157
- "content": "[ex13]",
158
  "single_word": false,
159
  "lstrip": false,
160
  "rstrip": false,
161
- "normalized": true,
162
- "special": false
163
  },
164
  {
165
  "id": 31986,
166
- "content": "[ex14]",
167
  "single_word": false,
168
  "lstrip": false,
169
  "rstrip": false,
170
- "normalized": true,
171
- "special": false
172
  },
173
  {
174
  "id": 31987,
175
- "content": "[ex15]",
176
  "single_word": false,
177
  "lstrip": false,
178
  "rstrip": false,
179
- "normalized": true,
180
- "special": false
181
  },
182
  {
183
  "id": 31988,
184
- "content": "[ex16]",
185
  "single_word": false,
186
  "lstrip": false,
187
  "rstrip": false,
188
- "normalized": true,
189
- "special": false
190
  },
191
  {
192
  "id": 31989,
193
- "content": "[ex17]",
194
  "single_word": false,
195
  "lstrip": false,
196
  "rstrip": false,
197
- "normalized": true,
198
- "special": false
199
  },
200
  {
201
  "id": 31990,
202
- "content": "[ex18]",
203
  "single_word": false,
204
  "lstrip": false,
205
  "rstrip": false,
206
- "normalized": true,
207
- "special": false
208
  },
209
  {
210
  "id": 31991,
211
- "content": "[ex19]",
212
  "single_word": false,
213
  "lstrip": false,
214
  "rstrip": false,
215
- "normalized": true,
216
- "special": false
217
  },
218
  {
219
  "id": 31992,
220
- "content": "[ex20]",
221
  "single_word": false,
222
  "lstrip": false,
223
  "rstrip": false,
224
- "normalized": true,
225
- "special": false
226
  },
227
  {
228
  "id": 31993,
229
- "content": "[ex21]",
230
  "single_word": false,
231
  "lstrip": false,
232
  "rstrip": false,
233
- "normalized": true,
234
- "special": false
235
  },
236
  {
237
  "id": 31994,
238
- "content": "[ex22]",
239
  "single_word": false,
240
  "lstrip": false,
241
  "rstrip": false,
242
- "normalized": true,
243
- "special": false
244
  },
245
  {
246
  "id": 31995,
247
- "content": "[ex23]",
248
  "single_word": false,
249
  "lstrip": false,
250
  "rstrip": false,
251
- "normalized": true,
252
- "special": false
253
  },
254
  {
255
  "id": 31996,
256
- "content": "[ex24]",
257
  "single_word": false,
258
  "lstrip": false,
259
  "rstrip": false,
260
- "normalized": true,
261
- "special": false
262
  },
263
  {
264
  "id": 31997,
265
- "content": "[ex25]",
266
  "single_word": false,
267
  "lstrip": false,
268
  "rstrip": false,
269
- "normalized": true,
270
- "special": false
271
  },
272
  {
273
  "id": 31998,
274
- "content": "[ex26]",
275
  "single_word": false,
276
  "lstrip": false,
277
  "rstrip": false,
278
- "normalized": true,
279
- "special": false
280
  },
281
  {
282
  "id": 31999,
283
- "content": "[ex27]",
284
  "single_word": false,
285
  "lstrip": false,
286
  "rstrip": false,
287
- "normalized": true,
288
- "special": false
289
  },
290
  {
291
  "id": 32000,
292
- "content": "[ex28]",
293
  "single_word": false,
294
  "lstrip": false,
295
  "rstrip": false,
296
- "normalized": true,
297
- "special": false
298
  },
299
  {
300
  "id": 32001,
301
- "content": "[ex29]",
302
  "single_word": false,
303
  "lstrip": false,
304
  "rstrip": false,
305
- "normalized": true,
306
- "special": false
307
  },
308
  {
309
  "id": 32002,
310
- "content": "[ex30]",
311
  "single_word": false,
312
  "lstrip": false,
313
  "rstrip": false,
314
- "normalized": true,
315
- "special": false
316
  },
317
  {
318
  "id": 32003,
319
- "content": "[ex31]",
320
  "single_word": false,
321
  "lstrip": false,
322
  "rstrip": false,
323
- "normalized": true,
324
- "special": false
325
  },
326
  {
327
  "id": 32004,
328
- "content": "[ex32]",
329
  "single_word": false,
330
  "lstrip": false,
331
  "rstrip": false,
332
- "normalized": true,
333
- "special": false
334
  },
335
  {
336
  "id": 32005,
337
- "content": "[ex33]",
338
  "single_word": false,
339
  "lstrip": false,
340
  "rstrip": false,
341
- "normalized": true,
342
- "special": false
343
  },
344
  {
345
  "id": 32006,
346
- "content": "[ex34]",
347
  "single_word": false,
348
  "lstrip": false,
349
  "rstrip": false,
350
- "normalized": true,
351
- "special": false
352
  },
353
  {
354
  "id": 32007,
355
- "content": "[ex35]",
356
  "single_word": false,
357
  "lstrip": false,
358
  "rstrip": false,
359
- "normalized": true,
360
- "special": false
361
  },
362
  {
363
  "id": 32008,
364
- "content": "[ex36]",
365
  "single_word": false,
366
  "lstrip": false,
367
  "rstrip": false,
368
- "normalized": true,
369
- "special": false
370
  },
371
  {
372
  "id": 32009,
373
- "content": "[ex37]",
374
  "single_word": false,
375
  "lstrip": false,
376
  "rstrip": false,
377
- "normalized": true,
378
- "special": false
379
  },
380
  {
381
  "id": 32010,
382
- "content": "[ex38]",
383
  "single_word": false,
384
  "lstrip": false,
385
  "rstrip": false,
386
- "normalized": true,
387
- "special": false
388
  },
389
  {
390
  "id": 32011,
391
- "content": "[ex39]",
392
  "single_word": false,
393
  "lstrip": false,
394
  "rstrip": false,
395
- "normalized": true,
396
- "special": false
397
  },
398
  {
399
  "id": 32012,
400
- "content": "[ex40]",
401
  "single_word": false,
402
  "lstrip": false,
403
  "rstrip": false,
404
- "normalized": true,
405
- "special": false
406
  },
407
  {
408
  "id": 32013,
409
- "content": "[ex41]",
410
  "single_word": false,
411
  "lstrip": false,
412
  "rstrip": false,
413
- "normalized": true,
414
- "special": false
415
  },
416
  {
417
  "id": 32014,
418
- "content": "[ex42]",
419
  "single_word": false,
420
  "lstrip": false,
421
  "rstrip": false,
422
- "normalized": true,
423
- "special": false
424
  },
425
  {
426
  "id": 32015,
427
- "content": "[ex43]",
428
  "single_word": false,
429
  "lstrip": false,
430
  "rstrip": false,
431
- "normalized": true,
432
- "special": false
433
  },
434
  {
435
  "id": 32016,
436
- "content": "[ex44]",
437
  "single_word": false,
438
  "lstrip": false,
439
  "rstrip": false,
440
- "normalized": true,
441
- "special": false
442
  },
443
  {
444
  "id": 32017,
445
- "content": "[ex45]",
446
  "single_word": false,
447
  "lstrip": false,
448
  "rstrip": false,
449
- "normalized": true,
450
- "special": false
451
  },
452
  {
453
  "id": 32018,
454
- "content": "[ex46]",
455
  "single_word": false,
456
  "lstrip": false,
457
  "rstrip": false,
458
- "normalized": true,
459
- "special": false
460
  },
461
  {
462
  "id": 32019,
463
- "content": "[ex47]",
464
  "single_word": false,
465
  "lstrip": false,
466
  "rstrip": false,
467
- "normalized": true,
468
- "special": false
469
  },
470
  {
471
  "id": 32020,
472
- "content": "[ex48]",
473
  "single_word": false,
474
  "lstrip": false,
475
  "rstrip": false,
476
- "normalized": true,
477
- "special": false
478
  },
479
  {
480
  "id": 32021,
481
- "content": "[ex49]",
482
  "single_word": false,
483
  "lstrip": false,
484
  "rstrip": false,
485
- "normalized": true,
486
- "special": false
487
  },
488
  {
489
  "id": 32022,
490
- "content": "[ex50]",
491
  "single_word": false,
492
  "lstrip": false,
493
  "rstrip": false,
494
- "normalized": true,
495
- "special": false
496
  },
497
  {
498
  "id": 32023,
499
- "content": "[ex51]",
500
  "single_word": false,
501
  "lstrip": false,
502
  "rstrip": false,
503
- "normalized": true,
504
- "special": false
505
  },
506
  {
507
  "id": 32024,
508
- "content": "[ex52]",
509
  "single_word": false,
510
  "lstrip": false,
511
  "rstrip": false,
512
- "normalized": true,
513
- "special": false
514
  },
515
  {
516
  "id": 32025,
517
- "content": "[ex53]",
518
  "single_word": false,
519
  "lstrip": false,
520
  "rstrip": false,
521
- "normalized": true,
522
- "special": false
523
  },
524
  {
525
  "id": 32026,
526
- "content": "[ex54]",
527
  "single_word": false,
528
  "lstrip": false,
529
  "rstrip": false,
530
- "normalized": true,
531
- "special": false
532
  },
533
  {
534
  "id": 32027,
535
- "content": "[ex55]",
536
  "single_word": false,
537
  "lstrip": false,
538
  "rstrip": false,
539
- "normalized": true,
540
- "special": false
541
  },
542
  {
543
  "id": 32028,
544
- "content": "[ex56]",
545
  "single_word": false,
546
  "lstrip": false,
547
  "rstrip": false,
548
- "normalized": true,
549
- "special": false
550
  },
551
  {
552
  "id": 32029,
553
- "content": "[ex57]",
554
  "single_word": false,
555
  "lstrip": false,
556
  "rstrip": false,
557
- "normalized": true,
558
- "special": false
559
  },
560
  {
561
  "id": 32030,
562
- "content": "[ex58]",
563
  "single_word": false,
564
  "lstrip": false,
565
  "rstrip": false,
566
- "normalized": true,
567
- "special": false
568
  },
569
  {
570
  "id": 32031,
571
- "content": "[ex59]",
572
  "single_word": false,
573
  "lstrip": false,
574
  "rstrip": false,
575
- "normalized": true,
576
- "special": false
577
  },
578
  {
579
  "id": 32032,
580
- "content": "[ex60]",
581
  "single_word": false,
582
  "lstrip": false,
583
  "rstrip": false,
584
- "normalized": true,
585
- "special": false
586
  },
587
  {
588
  "id": 32033,
589
- "content": "[ex61]",
590
  "single_word": false,
591
  "lstrip": false,
592
  "rstrip": false,
593
- "normalized": true,
594
- "special": false
595
- },
596
  {
597
  "id": 32034,
598
- "content": "[ex62]",
599
  "single_word": false,
600
  "lstrip": false,
601
  "rstrip": false,
602
- "normalized": true,
603
- "special": false
604
  },
605
  {
606
  "id": 32035,
607
- "content": "[ex63]",
608
  "single_word": false,
609
  "lstrip": false,
610
  "rstrip": false,
611
- "normalized": true,
612
- "special": false
613
  },
614
  {
615
  "id": 32036,
616
- "content": "[ex64]",
617
  "single_word": false,
618
  "lstrip": false,
619
  "rstrip": false,
620
- "normalized": true,
621
- "special": false
622
  },
623
  {
624
  "id": 32037,
625
- "content": "[ex65]",
626
  "single_word": false,
627
  "lstrip": false,
628
  "rstrip": false,
629
- "normalized": true,
630
- "special": false
631
  },
632
  {
633
  "id": 32038,
634
- "content": "[ex66]",
635
  "single_word": false,
636
  "lstrip": false,
637
  "rstrip": false,
638
- "normalized": true,
639
- "special": false
640
  },
641
  {
642
  "id": 32039,
643
- "content": "[ex67]",
644
  "single_word": false,
645
  "lstrip": false,
646
  "rstrip": false,
647
- "normalized": true,
648
- "special": false
649
  },
650
  {
651
  "id": 32040,
652
- "content": "[ex68]",
653
  "single_word": false,
654
  "lstrip": false,
655
  "rstrip": false,
656
- "normalized": true,
657
- "special": false
658
  },
659
  {
660
  "id": 32041,
661
- "content": "[ex69]",
662
  "single_word": false,
663
  "lstrip": false,
664
  "rstrip": false,
665
- "normalized": true,
666
- "special": false
667
  },
668
  {
669
  "id": 32042,
670
- "content": "[ex70]",
671
  "single_word": false,
672
  "lstrip": false,
673
  "rstrip": false,
674
- "normalized": true,
675
- "special": false
676
  },
677
  {
678
  "id": 32043,
679
- "content": "[ex71]",
680
  "single_word": false,
681
  "lstrip": false,
682
  "rstrip": false,
683
- "normalized": true,
684
- "special": false
685
  },
686
  {
687
  "id": 32044,
688
- "content": "[ex72]",
689
  "single_word": false,
690
  "lstrip": false,
691
  "rstrip": false,
692
- "normalized": true,
693
- "special": false
694
  },
695
  {
696
  "id": 32045,
697
- "content": "[ex73]",
698
  "single_word": false,
699
  "lstrip": false,
700
  "rstrip": false,
701
- "normalized": true,
702
- "special": false
703
  },
704
  {
705
  "id": 32046,
706
- "content": "[ex74]",
707
  "single_word": false,
708
  "lstrip": false,
709
  "rstrip": false,
710
- "normalized": true,
711
- "special": false
712
  },
713
  {
714
  "id": 32047,
715
- "content": "[ex75]",
716
  "single_word": false,
717
  "lstrip": false,
718
  "rstrip": false,
719
- "normalized": true,
720
- "special": false
721
  },
722
  {
723
  "id": 32048,
724
- "content": "[ex76]",
725
  "single_word": false,
726
  "lstrip": false,
727
  "rstrip": false,
728
- "normalized": true,
729
- "special": false
730
  },
731
  {
732
  "id": 32049,
733
- "content": "[ex77]",
734
  "single_word": false,
735
  "lstrip": false,
736
  "rstrip": false,
737
- "normalized": true,
738
- "special": false
739
  },
740
  {
741
  "id": 32050,
742
- "content": "[ex78]",
743
  "single_word": false,
744
  "lstrip": false,
745
  "rstrip": false,
746
- "normalized": true,
747
- "special": false
748
  },
749
  {
750
  "id": 32051,
751
- "content": "[ex79]",
752
  "single_word": false,
753
  "lstrip": false,
754
  "rstrip": false,
755
- "normalized": true,
756
- "special": false
757
  },
758
  {
759
  "id": 32052,
760
- "content": "[ex80]",
761
  "single_word": false,
762
  "lstrip": false,
763
  "rstrip": false,
764
- "normalized": true,
765
- "special": false
766
  },
767
  {
768
  "id": 32053,
769
- "content": "[ex81]",
770
  "single_word": false,
771
  "lstrip": false,
772
  "rstrip": false,
773
- "normalized": true,
774
- "special": false
775
  },
776
  {
777
  "id": 32054,
778
- "content": "[ex82]",
779
  "single_word": false,
780
  "lstrip": false,
781
  "rstrip": false,
782
- "normalized": true,
783
- "special": false
784
  },
785
  {
786
  "id": 32055,
787
- "content": "[ex83]",
788
  "single_word": false,
789
  "lstrip": false,
790
  "rstrip": false,
791
- "normalized": true,
792
- "special": false
793
  },
794
  {
795
  "id": 32056,
796
- "content": "[ex84]",
797
  "single_word": false,
798
  "lstrip": false,
799
  "rstrip": false,
800
- "normalized": true,
801
- "special": false
802
  },
803
  {
804
  "id": 32057,
805
- "content": "[ex85]",
806
  "single_word": false,
807
  "lstrip": false,
808
  "rstrip": false,
809
- "normalized": true,
810
- "special": false
811
  },
812
  {
813
  "id": 32058,
814
- "content": "[ex86]",
815
  "single_word": false,
816
  "lstrip": false,
817
  "rstrip": false,
818
- "normalized": true,
819
- "special": false
820
  },
821
  {
822
  "id": 32059,
823
- "content": "[ex87]",
824
  "single_word": false,
825
  "lstrip": false,
826
  "rstrip": false,
827
- "normalized": true,
828
- "special": false
829
  },
830
  {
831
  "id": 32060,
832
- "content": "[ex88]",
833
  "single_word": false,
834
  "lstrip": false,
835
  "rstrip": false,
836
- "normalized": true,
837
- "special": false
838
  },
839
  {
840
  "id": 32061,
841
- "content": "[ex89]",
842
  "single_word": false,
843
  "lstrip": false,
844
  "rstrip": false,
845
- "normalized": true,
846
- "special": false
847
  },
848
  {
849
  "id": 32062,
850
- "content": "[ex90]",
851
  "single_word": false,
852
  "lstrip": false,
853
  "rstrip": false,
854
- "normalized": true,
855
- "special": false
856
  },
857
  {
858
  "id": 32063,
859
- "content": "[ex91]",
860
  "single_word": false,
861
  "lstrip": false,
862
  "rstrip": false,
863
- "normalized": true,
864
- "special": false
865
  },
866
  {
867
  "id": 32064,
868
- "content": "[ex92]",
869
  "single_word": false,
870
  "lstrip": false,
871
  "rstrip": false,
872
- "normalized": true,
873
- "special": false
874
  },
875
  {
876
  "id": 32065,
877
- "content": "[ex93]",
878
  "single_word": false,
879
  "lstrip": false,
880
  "rstrip": false,
881
- "normalized": true,
882
- "special": false
883
  },
884
  {
885
  "id": 32066,
886
- "content": "[ex94]",
887
  "single_word": false,
888
  "lstrip": false,
889
  "rstrip": false,
890
- "normalized": true,
891
- "special": false
892
  },
893
  {
894
  "id": 32067,
895
- "content": "[ex95]",
896
  "single_word": false,
897
  "lstrip": false,
898
  "rstrip": false,
899
- "normalized": true,
900
- "special": false
901
  },
902
  {
903
  "id": 32068,
904
- "content": "[ex96]",
905
  "single_word": false,
906
  "lstrip": false,
907
  "rstrip": false,
908
- "normalized": true,
909
- "special": false
910
  },
911
  {
912
  "id": 32069,
913
- "content": "[ex97]",
914
  "single_word": false,
915
  "lstrip": false,
916
  "rstrip": false,
917
- "normalized": true,
918
- "special": false
919
  },
920
  {
921
  "id": 32070,
922
- "content": "[ex98]",
923
  "single_word": false,
924
  "lstrip": false,
925
  "rstrip": false,
926
- "normalized": true,
927
- "special": false
928
  },
929
  {
930
  "id": 32071,
931
- "content": "[ex99]",
932
  "single_word": false,
933
  "lstrip": false,
934
  "rstrip": false,
935
- "normalized": true,
936
- "special": false
937
  },
938
  {
939
  "id": 32072,
940
- "content": "ext.",
941
  "single_word": false,
942
  "lstrip": false,
943
  "rstrip": false,
944
- "normalized": true,
945
- "special": false
946
  },
947
  {
948
  "id": 32073,
949
- "content": "int.",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
950
  "single_word": false,
951
  "lstrip": false,
952
  "rstrip": false,
953
- "normalized": true,
954
- "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
955
  }
956
  ],
957
  "normalizer": null,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
14
  },
15
  {
16
  "id": 31970,
17
+ "content": "ext.",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
  },
24
  {
25
  "id": 31971,
26
+ "content": "int.",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
  },
33
  {
34
  "id": 31972,
35
+ "content": "[frl]",
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
  },
42
  {
43
  "id": 31973,
44
+ "content": "[mrl]",
45
  "single_word": false,
46
  "lstrip": false,
47
  "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
  },
51
  {
52
  "id": 31974,
53
+ "content": "[ex0]",
54
  "single_word": false,
55
  "lstrip": false,
56
  "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
  },
60
  {
61
  "id": 31975,
62
+ "content": "[ex1]",
63
  "single_word": false,
64
  "lstrip": false,
65
  "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
  },
69
  {
70
  "id": 31976,
71
+ "content": "[ex2]",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
  },
78
  {
79
  "id": 31977,
80
+ "content": "[ex3]",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
  },
87
  {
88
  "id": 31978,
89
+ "content": "[ex4]",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
  },
96
  {
97
  "id": 31979,
98
+ "content": "[ex5]",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
  },
105
  {
106
  "id": 31980,
107
+ "content": "[ex6]",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
  },
114
  {
115
  "id": 31981,
116
+ "content": "[ex7]",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
  },
123
  {
124
  "id": 31982,
125
+ "content": "[ex8]",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
  },
132
  {
133
  "id": 31983,
134
+ "content": "[ex9]",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
  },
141
  {
142
  "id": 31984,
143
+ "content": "[ex10]",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
  },
150
  {
151
  "id": 31985,
152
+ "content": "[ex11]",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
  },
159
  {
160
  "id": 31986,
161
+ "content": "[ex12]",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
  },
168
  {
169
  "id": 31987,
170
+ "content": "[ex13]",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
  },
177
  {
178
  "id": 31988,
179
+ "content": "[ex14]",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
  },
186
  {
187
  "id": 31989,
188
+ "content": "[ex15]",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
  },
195
  {
196
  "id": 31990,
197
+ "content": "[ex16]",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
  },
204
  {
205
  "id": 31991,
206
+ "content": "[ex17]",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
  },
213
  {
214
  "id": 31992,
215
+ "content": "[ex18]",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
  },
222
  {
223
  "id": 31993,
224
+ "content": "[ex19]",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
  },
231
  {
232
  "id": 31994,
233
+ "content": "[ex20]",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
  },
240
  {
241
  "id": 31995,
242
+ "content": "[ex21]",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
  },
249
  {
250
  "id": 31996,
251
+ "content": "[ex22]",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
  },
258
  {
259
  "id": 31997,
260
+ "content": "[ex23]",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
  },
267
  {
268
  "id": 31998,
269
+ "content": "[ex24]",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
  },
276
  {
277
  "id": 31999,
278
+ "content": "[ex25]",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
  },
285
  {
286
  "id": 32000,
287
+ "content": "[ex26]",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
  },
294
  {
295
  "id": 32001,
296
+ "content": "[ex27]",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
  },
303
  {
304
  "id": 32002,
305
+ "content": "[ex28]",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
  },
312
  {
313
  "id": 32003,
314
+ "content": "[ex29]",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
  },
321
  {
322
  "id": 32004,
323
+ "content": "[ex30]",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
  },
330
  {
331
  "id": 32005,
332
+ "content": "[ex31]",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
  },
339
  {
340
  "id": 32006,
341
+ "content": "[ex32]",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
  },
348
  {
349
  "id": 32007,
350
+ "content": "[ex33]",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
  },
357
  {
358
  "id": 32008,
359
+ "content": "[ex34]",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
  },
366
  {
367
  "id": 32009,
368
+ "content": "[ex35]",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
  },
375
  {
376
  "id": 32010,
377
+ "content": "[ex36]",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
  },
384
  {
385
  "id": 32011,
386
+ "content": "[ex37]",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
  },
393
  {
394
  "id": 32012,
395
+ "content": "[ex38]",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
  },
402
  {
403
  "id": 32013,
404
+ "content": "[ex39]",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
  },
411
  {
412
  "id": 32014,
413
+ "content": "[ex40]",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
  },
420
  {
421
  "id": 32015,
422
+ "content": "[ex41]",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
  },
429
  {
430
  "id": 32016,
431
+ "content": "[ex42]",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
  },
438
  {
439
  "id": 32017,
440
+ "content": "[ex43]",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
  },
447
  {
448
  "id": 32018,
449
+ "content": "[ex44]",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
  },
456
  {
457
  "id": 32019,
458
+ "content": "[ex45]",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
  },
465
  {
466
  "id": 32020,
467
+ "content": "[ex46]",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
  },
474
  {
475
  "id": 32021,
476
+ "content": "[ex47]",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
  },
483
  {
484
  "id": 32022,
485
+ "content": "[ex48]",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
  },
492
  {
493
  "id": 32023,
494
+ "content": "[ex49]",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
  },
501
  {
502
  "id": 32024,
503
+ "content": "[ex50]",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
  },
510
  {
511
  "id": 32025,
512
+ "content": "[ex51]",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
  },
519
  {
520
  "id": 32026,
521
+ "content": "[ex52]",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
  },
528
  {
529
  "id": 32027,
530
+ "content": "[ex53]",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
  },
537
  {
538
  "id": 32028,
539
+ "content": "[ex54]",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
  },
546
  {
547
  "id": 32029,
548
+ "content": "[ex55]",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
  },
555
  {
556
  "id": 32030,
557
+ "content": "[ex56]",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
  },
564
  {
565
  "id": 32031,
566
+ "content": "[ex57]",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
  },
573
  {
574
  "id": 32032,
575
+ "content": "[ex58]",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
  },
582
  {
583
  "id": 32033,
584
+ "content": "[ex59]",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
  {
592
  "id": 32034,
593
+ "content": "[ex60]",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
  },
600
  {
601
  "id": 32035,
602
+ "content": "[ex61]",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
  },
609
  {
610
  "id": 32036,
611
+ "content": "[ex62]",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
  },
618
  {
619
  "id": 32037,
620
+ "content": "[ex63]",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
  },
627
  {
628
  "id": 32038,
629
+ "content": "[ex64]",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
  },
636
  {
637
  "id": 32039,
638
+ "content": "[ex65]",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
  },
645
  {
646
  "id": 32040,
647
+ "content": "[ex66]",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
  },
654
  {
655
  "id": 32041,
656
+ "content": "[ex67]",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
  },
663
  {
664
  "id": 32042,
665
+ "content": "[ex68]",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
  },
672
  {
673
  "id": 32043,
674
+ "content": "[ex69]",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
  },
681
  {
682
  "id": 32044,
683
+ "content": "[ex70]",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
  },
690
  {
691
  "id": 32045,
692
+ "content": "[ex71]",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
  },
699
  {
700
  "id": 32046,
701
+ "content": "[ex72]",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
  },
708
  {
709
  "id": 32047,
710
+ "content": "[ex73]",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
  },
717
  {
718
  "id": 32048,
719
+ "content": "[ex74]",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
  },
726
  {
727
  "id": 32049,
728
+ "content": "[ex75]",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
  },
735
  {
736
  "id": 32050,
737
+ "content": "[ex76]",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
  },
744
  {
745
  "id": 32051,
746
+ "content": "[ex77]",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
  },
753
  {
754
  "id": 32052,
755
+ "content": "[ex78]",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
  },
762
  {
763
  "id": 32053,
764
+ "content": "[ex79]",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
  },
771
  {
772
  "id": 32054,
773
+ "content": "[ex80]",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
  },
780
  {
781
  "id": 32055,
782
+ "content": "[ex81]",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
  },
789
  {
790
  "id": 32056,
791
+ "content": "[ex82]",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
  },
798
  {
799
  "id": 32057,
800
+ "content": "[ex83]",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
  },
807
  {
808
  "id": 32058,
809
+ "content": "[ex84]",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
  },
816
  {
817
  "id": 32059,
818
+ "content": "[ex85]",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
  },
825
  {
826
  "id": 32060,
827
+ "content": "[ex86]",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
  },
834
  {
835
  "id": 32061,
836
+ "content": "[ex87]",
837
  "single_word": false,
838
  "lstrip": false,
839
  "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
  },
843
  {
844
  "id": 32062,
845
+ "content": "[ex88]",
846
  "single_word": false,
847
  "lstrip": false,
848
  "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
  },
852
  {
853
  "id": 32063,
854
+ "content": "[ex89]",
855
  "single_word": false,
856
  "lstrip": false,
857
  "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
  },
861
  {
862
  "id": 32064,
863
+ "content": "[ex90]",
864
  "single_word": false,
865
  "lstrip": false,
866
  "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
  },
870
  {
871
  "id": 32065,
872
+ "content": "[ex91]",
873
  "single_word": false,
874
  "lstrip": false,
875
  "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
  },
879
  {
880
  "id": 32066,
881
+ "content": "[ex92]",
882
  "single_word": false,
883
  "lstrip": false,
884
  "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
  },
888
  {
889
  "id": 32067,
890
+ "content": "[ex93]",
891
  "single_word": false,
892
  "lstrip": false,
893
  "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
  },
897
  {
898
  "id": 32068,
899
+ "content": "[ex94]",
900
  "single_word": false,
901
  "lstrip": false,
902
  "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
  },
906
  {
907
  "id": 32069,
908
+ "content": "[ex95]",
909
  "single_word": false,
910
  "lstrip": false,
911
  "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
  },
915
  {
916
  "id": 32070,
917
+ "content": "[ex96]",
918
  "single_word": false,
919
  "lstrip": false,
920
  "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
  },
924
  {
925
  "id": 32071,
926
+ "content": "[ex97]",
927
  "single_word": false,
928
  "lstrip": false,
929
  "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
  },
933
  {
934
  "id": 32072,
935
+ "content": "[ex98]",
936
  "single_word": false,
937
  "lstrip": false,
938
  "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
  },
942
  {
943
  "id": 32073,
944
+ "content": "[ex99]",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 32074,
953
+ "content": "[frl]:",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 32075,
962
+ "content": "[mrl]:",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 32076,
971
+ "content": "[ex0]:",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 32077,
980
+ "content": "[ex1]:",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 32078,
989
+ "content": "[ex2]:",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 32079,
998
+ "content": "[ex3]:",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 32080,
1007
+ "content": "[ex4]:",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 32081,
1016
+ "content": "[ex5]:",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 32082,
1025
+ "content": "[ex6]:",
1026
  "single_word": false,
1027
  "lstrip": false,
1028
  "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 32083,
1034
+ "content": "[ex7]:",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 32084,
1043
+ "content": "[ex8]:",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 32085,
1052
+ "content": "[ex9]:",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 32086,
1061
+ "content": "[ex10]:",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 32087,
1070
+ "content": "[ex11]:",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ },
1077
+ {
1078
+ "id": 32088,
1079
+ "content": "[ex12]:",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": false,
1084
+ "special": true
1085
+ },
1086
+ {
1087
+ "id": 32089,
1088
+ "content": "[ex13]:",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": false,
1093
+ "special": true
1094
+ },
1095
+ {
1096
+ "id": 32090,
1097
+ "content": "[ex14]:",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": false,
1102
+ "special": true
1103
+ },
1104
+ {
1105
+ "id": 32091,
1106
+ "content": "[ex15]:",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": false,
1111
+ "special": true
1112
+ },
1113
+ {
1114
+ "id": 32092,
1115
+ "content": "[ex16]:",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": false,
1120
+ "special": true
1121
+ },
1122
+ {
1123
+ "id": 32093,
1124
+ "content": "[ex17]:",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": false,
1129
+ "special": true
1130
+ },
1131
+ {
1132
+ "id": 32094,
1133
+ "content": "[ex18]:",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": false,
1138
+ "special": true
1139
+ },
1140
+ {
1141
+ "id": 32095,
1142
+ "content": "[ex19]:",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": false,
1147
+ "special": true
1148
+ },
1149
+ {
1150
+ "id": 32096,
1151
+ "content": "[ex20]:",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": false,
1156
+ "special": true
1157
+ },
1158
+ {
1159
+ "id": 32097,
1160
+ "content": "[ex21]:",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": false,
1165
+ "special": true
1166
+ },
1167
+ {
1168
+ "id": 32098,
1169
+ "content": "[ex22]:",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": false,
1174
+ "special": true
1175
+ },
1176
+ {
1177
+ "id": 32099,
1178
+ "content": "[ex23]:",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": false,
1183
+ "special": true
1184
+ },
1185
+ {
1186
+ "id": 32100,
1187
+ "content": "[ex24]:",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": false,
1192
+ "special": true
1193
+ },
1194
+ {
1195
+ "id": 32101,
1196
+ "content": "[ex25]:",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": false,
1201
+ "special": true
1202
+ },
1203
+ {
1204
+ "id": 32102,
1205
+ "content": "[ex26]:",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": false,
1210
+ "special": true
1211
+ },
1212
+ {
1213
+ "id": 32103,
1214
+ "content": "[ex27]:",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": false,
1219
+ "special": true
1220
+ },
1221
+ {
1222
+ "id": 32104,
1223
+ "content": "[ex28]:",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": false,
1228
+ "special": true
1229
+ },
1230
+ {
1231
+ "id": 32105,
1232
+ "content": "[ex29]:",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": false,
1237
+ "special": true
1238
+ },
1239
+ {
1240
+ "id": 32106,
1241
+ "content": "[ex30]:",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": false,
1246
+ "special": true
1247
+ },
1248
+ {
1249
+ "id": 32107,
1250
+ "content": "[ex31]:",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": false,
1255
+ "special": true
1256
+ },
1257
+ {
1258
+ "id": 32108,
1259
+ "content": "[ex32]:",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": false,
1264
+ "special": true
1265
+ },
1266
+ {
1267
+ "id": 32109,
1268
+ "content": "[ex33]:",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": false,
1273
+ "special": true
1274
+ },
1275
+ {
1276
+ "id": 32110,
1277
+ "content": "[ex34]:",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": false,
1282
+ "special": true
1283
+ },
1284
+ {
1285
+ "id": 32111,
1286
+ "content": "[ex35]:",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": false,
1291
+ "special": true
1292
+ },
1293
+ {
1294
+ "id": 32112,
1295
+ "content": "[ex36]:",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": false,
1300
+ "special": true
1301
+ },
1302
+ {
1303
+ "id": 32113,
1304
+ "content": "[ex37]:",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": false,
1309
+ "special": true
1310
+ },
1311
+ {
1312
+ "id": 32114,
1313
+ "content": "[ex38]:",
1314
+ "single_word": false,
1315
+ "lstrip": false,
1316
+ "rstrip": false,
1317
+ "normalized": false,
1318
+ "special": true
1319
+ },
1320
+ {
1321
+ "id": 32115,
1322
+ "content": "[ex39]:",
1323
+ "single_word": false,
1324
+ "lstrip": false,
1325
+ "rstrip": false,
1326
+ "normalized": false,
1327
+ "special": true
1328
+ },
1329
+ {
1330
+ "id": 32116,
1331
+ "content": "[ex40]:",
1332
+ "single_word": false,
1333
+ "lstrip": false,
1334
+ "rstrip": false,
1335
+ "normalized": false,
1336
+ "special": true
1337
+ },
1338
+ {
1339
+ "id": 32117,
1340
+ "content": "[ex41]:",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": false,
1345
+ "special": true
1346
+ },
1347
+ {
1348
+ "id": 32118,
1349
+ "content": "[ex42]:",
1350
+ "single_word": false,
1351
+ "lstrip": false,
1352
+ "rstrip": false,
1353
+ "normalized": false,
1354
+ "special": true
1355
+ },
1356
+ {
1357
+ "id": 32119,
1358
+ "content": "[ex43]:",
1359
+ "single_word": false,
1360
+ "lstrip": false,
1361
+ "rstrip": false,
1362
+ "normalized": false,
1363
+ "special": true
1364
+ },
1365
+ {
1366
+ "id": 32120,
1367
+ "content": "[ex44]:",
1368
+ "single_word": false,
1369
+ "lstrip": false,
1370
+ "rstrip": false,
1371
+ "normalized": false,
1372
+ "special": true
1373
+ },
1374
+ {
1375
+ "id": 32121,
1376
+ "content": "[ex45]:",
1377
+ "single_word": false,
1378
+ "lstrip": false,
1379
+ "rstrip": false,
1380
+ "normalized": false,
1381
+ "special": true
1382
+ },
1383
+ {
1384
+ "id": 32122,
1385
+ "content": "[ex46]:",
1386
+ "single_word": false,
1387
+ "lstrip": false,
1388
+ "rstrip": false,
1389
+ "normalized": false,
1390
+ "special": true
1391
+ },
1392
+ {
1393
+ "id": 32123,
1394
+ "content": "[ex47]:",
1395
+ "single_word": false,
1396
+ "lstrip": false,
1397
+ "rstrip": false,
1398
+ "normalized": false,
1399
+ "special": true
1400
+ },
1401
+ {
1402
+ "id": 32124,
1403
+ "content": "[ex48]:",
1404
+ "single_word": false,
1405
+ "lstrip": false,
1406
+ "rstrip": false,
1407
+ "normalized": false,
1408
+ "special": true
1409
+ },
1410
+ {
1411
+ "id": 32125,
1412
+ "content": "[ex49]:",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": false,
1417
+ "special": true
1418
+ },
1419
+ {
1420
+ "id": 32126,
1421
+ "content": "[ex50]:",
1422
+ "single_word": false,
1423
+ "lstrip": false,
1424
+ "rstrip": false,
1425
+ "normalized": false,
1426
+ "special": true
1427
+ },
1428
+ {
1429
+ "id": 32127,
1430
+ "content": "[ex51]:",
1431
+ "single_word": false,
1432
+ "lstrip": false,
1433
+ "rstrip": false,
1434
+ "normalized": false,
1435
+ "special": true
1436
+ },
1437
+ {
1438
+ "id": 32128,
1439
+ "content": "[ex52]:",
1440
+ "single_word": false,
1441
+ "lstrip": false,
1442
+ "rstrip": false,
1443
+ "normalized": false,
1444
+ "special": true
1445
+ },
1446
+ {
1447
+ "id": 32129,
1448
+ "content": "[ex53]:",
1449
+ "single_word": false,
1450
+ "lstrip": false,
1451
+ "rstrip": false,
1452
+ "normalized": false,
1453
+ "special": true
1454
+ },
1455
+ {
1456
+ "id": 32130,
1457
+ "content": "[ex54]:",
1458
+ "single_word": false,
1459
+ "lstrip": false,
1460
+ "rstrip": false,
1461
+ "normalized": false,
1462
+ "special": true
1463
+ },
1464
+ {
1465
+ "id": 32131,
1466
+ "content": "[ex55]:",
1467
+ "single_word": false,
1468
+ "lstrip": false,
1469
+ "rstrip": false,
1470
+ "normalized": false,
1471
+ "special": true
1472
+ },
1473
+ {
1474
+ "id": 32132,
1475
+ "content": "[ex56]:",
1476
+ "single_word": false,
1477
+ "lstrip": false,
1478
+ "rstrip": false,
1479
+ "normalized": false,
1480
+ "special": true
1481
+ },
1482
+ {
1483
+ "id": 32133,
1484
+ "content": "[ex57]:",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": false,
1489
+ "special": true
1490
+ },
1491
+ {
1492
+ "id": 32134,
1493
+ "content": "[ex58]:",
1494
+ "single_word": false,
1495
+ "lstrip": false,
1496
+ "rstrip": false,
1497
+ "normalized": false,
1498
+ "special": true
1499
+ },
1500
+ {
1501
+ "id": 32135,
1502
+ "content": "[ex59]:",
1503
+ "single_word": false,
1504
+ "lstrip": false,
1505
+ "rstrip": false,
1506
+ "normalized": false,
1507
+ "special": true
1508
+ },
1509
+ {
1510
+ "id": 32136,
1511
+ "content": "[ex60]:",
1512
+ "single_word": false,
1513
+ "lstrip": false,
1514
+ "rstrip": false,
1515
+ "normalized": false,
1516
+ "special": true
1517
+ },
1518
+ {
1519
+ "id": 32137,
1520
+ "content": "[ex61]:",
1521
+ "single_word": false,
1522
+ "lstrip": false,
1523
+ "rstrip": false,
1524
+ "normalized": false,
1525
+ "special": true
1526
+ },
1527
+ {
1528
+ "id": 32138,
1529
+ "content": "[ex62]:",
1530
+ "single_word": false,
1531
+ "lstrip": false,
1532
+ "rstrip": false,
1533
+ "normalized": false,
1534
+ "special": true
1535
+ },
1536
+ {
1537
+ "id": 32139,
1538
+ "content": "[ex63]:",
1539
+ "single_word": false,
1540
+ "lstrip": false,
1541
+ "rstrip": false,
1542
+ "normalized": false,
1543
+ "special": true
1544
+ },
1545
+ {
1546
+ "id": 32140,
1547
+ "content": "[ex64]:",
1548
+ "single_word": false,
1549
+ "lstrip": false,
1550
+ "rstrip": false,
1551
+ "normalized": false,
1552
+ "special": true
1553
+ },
1554
+ {
1555
+ "id": 32141,
1556
+ "content": "[ex65]:",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": false,
1561
+ "special": true
1562
+ },
1563
+ {
1564
+ "id": 32142,
1565
+ "content": "[ex66]:",
1566
+ "single_word": false,
1567
+ "lstrip": false,
1568
+ "rstrip": false,
1569
+ "normalized": false,
1570
+ "special": true
1571
+ },
1572
+ {
1573
+ "id": 32143,
1574
+ "content": "[ex67]:",
1575
+ "single_word": false,
1576
+ "lstrip": false,
1577
+ "rstrip": false,
1578
+ "normalized": false,
1579
+ "special": true
1580
+ },
1581
+ {
1582
+ "id": 32144,
1583
+ "content": "[ex68]:",
1584
+ "single_word": false,
1585
+ "lstrip": false,
1586
+ "rstrip": false,
1587
+ "normalized": false,
1588
+ "special": true
1589
+ },
1590
+ {
1591
+ "id": 32145,
1592
+ "content": "[ex69]:",
1593
+ "single_word": false,
1594
+ "lstrip": false,
1595
+ "rstrip": false,
1596
+ "normalized": false,
1597
+ "special": true
1598
+ },
1599
+ {
1600
+ "id": 32146,
1601
+ "content": "[ex70]:",
1602
+ "single_word": false,
1603
+ "lstrip": false,
1604
+ "rstrip": false,
1605
+ "normalized": false,
1606
+ "special": true
1607
+ },
1608
+ {
1609
+ "id": 32147,
1610
+ "content": "[ex71]:",
1611
+ "single_word": false,
1612
+ "lstrip": false,
1613
+ "rstrip": false,
1614
+ "normalized": false,
1615
+ "special": true
1616
+ },
1617
+ {
1618
+ "id": 32148,
1619
+ "content": "[ex72]:",
1620
+ "single_word": false,
1621
+ "lstrip": false,
1622
+ "rstrip": false,
1623
+ "normalized": false,
1624
+ "special": true
1625
+ },
1626
+ {
1627
+ "id": 32149,
1628
+ "content": "[ex73]:",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": false,
1633
+ "special": true
1634
+ },
1635
+ {
1636
+ "id": 32150,
1637
+ "content": "[ex74]:",
1638
+ "single_word": false,
1639
+ "lstrip": false,
1640
+ "rstrip": false,
1641
+ "normalized": false,
1642
+ "special": true
1643
+ },
1644
+ {
1645
+ "id": 32151,
1646
+ "content": "[ex75]:",
1647
+ "single_word": false,
1648
+ "lstrip": false,
1649
+ "rstrip": false,
1650
+ "normalized": false,
1651
+ "special": true
1652
+ },
1653
+ {
1654
+ "id": 32152,
1655
+ "content": "[ex76]:",
1656
+ "single_word": false,
1657
+ "lstrip": false,
1658
+ "rstrip": false,
1659
+ "normalized": false,
1660
+ "special": true
1661
+ },
1662
+ {
1663
+ "id": 32153,
1664
+ "content": "[ex77]:",
1665
+ "single_word": false,
1666
+ "lstrip": false,
1667
+ "rstrip": false,
1668
+ "normalized": false,
1669
+ "special": true
1670
+ },
1671
+ {
1672
+ "id": 32154,
1673
+ "content": "[ex78]:",
1674
+ "single_word": false,
1675
+ "lstrip": false,
1676
+ "rstrip": false,
1677
+ "normalized": false,
1678
+ "special": true
1679
+ },
1680
+ {
1681
+ "id": 32155,
1682
+ "content": "[ex79]:",
1683
+ "single_word": false,
1684
+ "lstrip": false,
1685
+ "rstrip": false,
1686
+ "normalized": false,
1687
+ "special": true
1688
+ },
1689
+ {
1690
+ "id": 32156,
1691
+ "content": "[ex80]:",
1692
+ "single_word": false,
1693
+ "lstrip": false,
1694
+ "rstrip": false,
1695
+ "normalized": false,
1696
+ "special": true
1697
+ },
1698
+ {
1699
+ "id": 32157,
1700
+ "content": "[ex81]:",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": false,
1705
+ "special": true
1706
+ },
1707
+ {
1708
+ "id": 32158,
1709
+ "content": "[ex82]:",
1710
+ "single_word": false,
1711
+ "lstrip": false,
1712
+ "rstrip": false,
1713
+ "normalized": false,
1714
+ "special": true
1715
+ },
1716
+ {
1717
+ "id": 32159,
1718
+ "content": "[ex83]:",
1719
+ "single_word": false,
1720
+ "lstrip": false,
1721
+ "rstrip": false,
1722
+ "normalized": false,
1723
+ "special": true
1724
+ },
1725
+ {
1726
+ "id": 32160,
1727
+ "content": "[ex84]:",
1728
+ "single_word": false,
1729
+ "lstrip": false,
1730
+ "rstrip": false,
1731
+ "normalized": false,
1732
+ "special": true
1733
+ },
1734
+ {
1735
+ "id": 32161,
1736
+ "content": "[ex85]:",
1737
+ "single_word": false,
1738
+ "lstrip": false,
1739
+ "rstrip": false,
1740
+ "normalized": false,
1741
+ "special": true
1742
+ },
1743
+ {
1744
+ "id": 32162,
1745
+ "content": "[ex86]:",
1746
+ "single_word": false,
1747
+ "lstrip": false,
1748
+ "rstrip": false,
1749
+ "normalized": false,
1750
+ "special": true
1751
+ },
1752
+ {
1753
+ "id": 32163,
1754
+ "content": "[ex87]:",
1755
+ "single_word": false,
1756
+ "lstrip": false,
1757
+ "rstrip": false,
1758
+ "normalized": false,
1759
+ "special": true
1760
+ },
1761
+ {
1762
+ "id": 32164,
1763
+ "content": "[ex88]:",
1764
+ "single_word": false,
1765
+ "lstrip": false,
1766
+ "rstrip": false,
1767
+ "normalized": false,
1768
+ "special": true
1769
+ },
1770
+ {
1771
+ "id": 32165,
1772
+ "content": "[ex89]:",
1773
+ "single_word": false,
1774
+ "lstrip": false,
1775
+ "rstrip": false,
1776
+ "normalized": false,
1777
+ "special": true
1778
+ },
1779
+ {
1780
+ "id": 32166,
1781
+ "content": "[ex90]:",
1782
+ "single_word": false,
1783
+ "lstrip": false,
1784
+ "rstrip": false,
1785
+ "normalized": false,
1786
+ "special": true
1787
+ },
1788
+ {
1789
+ "id": 32167,
1790
+ "content": "[ex91]:",
1791
+ "single_word": false,
1792
+ "lstrip": false,
1793
+ "rstrip": false,
1794
+ "normalized": false,
1795
+ "special": true
1796
+ },
1797
+ {
1798
+ "id": 32168,
1799
+ "content": "[ex92]:",
1800
+ "single_word": false,
1801
+ "lstrip": false,
1802
+ "rstrip": false,
1803
+ "normalized": false,
1804
+ "special": true
1805
+ },
1806
+ {
1807
+ "id": 32169,
1808
+ "content": "[ex93]:",
1809
+ "single_word": false,
1810
+ "lstrip": false,
1811
+ "rstrip": false,
1812
+ "normalized": false,
1813
+ "special": true
1814
+ },
1815
+ {
1816
+ "id": 32170,
1817
+ "content": "[ex94]:",
1818
+ "single_word": false,
1819
+ "lstrip": false,
1820
+ "rstrip": false,
1821
+ "normalized": false,
1822
+ "special": true
1823
+ },
1824
+ {
1825
+ "id": 32171,
1826
+ "content": "[ex95]:",
1827
+ "single_word": false,
1828
+ "lstrip": false,
1829
+ "rstrip": false,
1830
+ "normalized": false,
1831
+ "special": true
1832
+ },
1833
+ {
1834
+ "id": 32172,
1835
+ "content": "[ex96]:",
1836
+ "single_word": false,
1837
+ "lstrip": false,
1838
+ "rstrip": false,
1839
+ "normalized": false,
1840
+ "special": true
1841
+ },
1842
+ {
1843
+ "id": 32173,
1844
+ "content": "[ex97]:",
1845
+ "single_word": false,
1846
+ "lstrip": false,
1847
+ "rstrip": false,
1848
+ "normalized": false,
1849
+ "special": true
1850
+ },
1851
+ {
1852
+ "id": 32174,
1853
+ "content": "[ex98]:",
1854
+ "single_word": false,
1855
+ "lstrip": false,
1856
+ "rstrip": false,
1857
+ "normalized": false,
1858
+ "special": true
1859
+ },
1860
+ {
1861
+ "id": 32175,
1862
+ "content": "[ex99]:",
1863
+ "single_word": false,
1864
+ "lstrip": false,
1865
+ "rstrip": false,
1866
+ "normalized": false,
1867
+ "special": true
1868
  }
1869
  ],
1870
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
- "name_or_path": "MarkGG/Romance-cleaned-3",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
 
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"