Commit
•
3ec53c1
1
Parent(s):
d609a52
End of training
Browse files- README.md +8 -12
- added_tokens.json +16 -54
- special_tokens_map.json +17 -283
- tokenizer.json +16 -358
- tokenizer_config.json +33 -375
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -42,22 +42,18 @@ The following hyperparameters were used during training:
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 6.
|
52 |
-
| 3.
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 0.9245 | 7.0 | 315 | 1.1895 |
|
58 |
-
| 0.4144 | 8.0 | 360 | 1.2128 |
|
59 |
-
| 0.4087 | 9.0 | 405 | 1.1811 |
|
60 |
-
| 0.4926 | 10.0 | 450 | 1.1461 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.5746
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 6
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 6.9386 | 1.0 | 40 | 6.1254 |
|
52 |
+
| 3.8907 | 2.0 | 80 | 3.3437 |
|
53 |
+
| 3.0701 | 3.0 | 120 | 2.8495 |
|
54 |
+
| 2.6156 | 4.0 | 160 | 2.7129 |
|
55 |
+
| 2.3074 | 5.0 | 200 | 2.6461 |
|
56 |
+
| 2.2406 | 6.0 | 240 | 2.5746 |
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
added_tokens.json
CHANGED
@@ -1,59 +1,21 @@
|
|
1 |
{
|
2 |
-
"</
|
3 |
-
"</
|
4 |
-
"</
|
5 |
-
"</
|
6 |
-
"</
|
7 |
-
"</
|
8 |
-
"</
|
9 |
-
"</
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"</s_father_nationalty>": 57555,
|
14 |
-
"</s_father_occupaation>": 57568,
|
15 |
-
"</s_father_occupation>": 57531,
|
16 |
-
"</s_father_race>": 57560,
|
17 |
-
"</s_father_religion>": 57528,
|
18 |
-
"</s_mother-nationality>": 57556,
|
19 |
-
"</s_mother_age>": 57554,
|
20 |
-
"</s_mother_birthplace>": 57552,
|
21 |
-
"</s_mother_first_name>": 57551,
|
22 |
-
"</s_mother_last_name>": 57548,
|
23 |
-
"</s_mother_middle_name>": 57558,
|
24 |
-
"</s_mother_nationality>": 57537,
|
25 |
-
"</s_mother_nationalty>": 57566,
|
26 |
-
"</s_mother_race>": 57534,
|
27 |
-
"</s_mother_religion>": 57575,
|
28 |
-
"</s_province>": 57576,
|
29 |
-
"<s_DOB>": 57546,
|
30 |
-
"<s_child_first_name>": 57557,
|
31 |
-
"<s_child_last_name>": 57544,
|
32 |
-
"<s_child_middle_name>": 57545,
|
33 |
-
"<s_city>": 57550,
|
34 |
-
"<s_father_age>": 57577,
|
35 |
-
"<s_father_birthplace>": 57573,
|
36 |
-
"<s_father_first_name>": 57538,
|
37 |
-
"<s_father_last_name>": 57527,
|
38 |
-
"<s_father_middle_name>": 57559,
|
39 |
-
"<s_father_nationality>": 57539,
|
40 |
-
"<s_father_nationalty>": 57571,
|
41 |
-
"<s_father_occupaation>": 57541,
|
42 |
-
"<s_father_occupation>": 57561,
|
43 |
-
"<s_father_race>": 57549,
|
44 |
-
"<s_father_religion>": 57564,
|
45 |
"<s_iitcdip>": 57523,
|
46 |
-
"<
|
47 |
-
"<
|
48 |
-
"<
|
49 |
-
"<
|
50 |
-
"<s_mother_last_name>": 57526,
|
51 |
-
"<s_mother_middle_name>": 57542,
|
52 |
-
"<s_mother_nationality>": 57529,
|
53 |
-
"<s_mother_nationalty>": 57569,
|
54 |
-
"<s_mother_race>": 57533,
|
55 |
-
"<s_mother_religion>": 57536,
|
56 |
-
"<s_province>": 57525,
|
57 |
"<s_synthdog>": 57524,
|
|
|
58 |
"<sep/>": 57522
|
59 |
}
|
|
|
1 |
{
|
2 |
+
"</s_address>": 57530,
|
3 |
+
"</s_father_name>": 57537,
|
4 |
+
"</s_first_name>": 57534,
|
5 |
+
"</s_last_name>": 57539,
|
6 |
+
"</s_mother_name>": 57531,
|
7 |
+
"</s_place_of_birth>": 57540,
|
8 |
+
"</s_random_number>": 57532,
|
9 |
+
"</s_title>": 57536,
|
10 |
+
"<s_address>": 57538,
|
11 |
+
"<s_father_name>": 57526,
|
12 |
+
"<s_first_name>": 57527,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"<s_iitcdip>": 57523,
|
14 |
+
"<s_last_name>": 57535,
|
15 |
+
"<s_mother_name>": 57525,
|
16 |
+
"<s_place_of_birth>": 57529,
|
17 |
+
"<s_random_number>": 57528,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"<s_synthdog>": 57524,
|
19 |
+
"<s_title>": 57533,
|
20 |
"<sep/>": 57522
|
21 |
}
|
special_tokens_map.json
CHANGED
@@ -1,189 +1,105 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
{
|
4 |
-
"content": "<
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
10 |
{
|
11 |
-
"content": "<
|
12 |
"lstrip": false,
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
},
|
17 |
{
|
18 |
-
"content": "<
|
19 |
"lstrip": false,
|
20 |
"normalized": false,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
{
|
25 |
-
"content": "</
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"content": "<s_mother_nationality>",
|
33 |
-
"lstrip": false,
|
34 |
-
"normalized": false,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"content": "</s_father_first_name>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false
|
44 |
-
},
|
45 |
-
{
|
46 |
-
"content": "</s_father_occupation>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"content": "</s_child_first_name>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"content": "<s_mother_race>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"content": "</s_mother_race>",
|
68 |
-
"lstrip": false,
|
69 |
-
"normalized": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"single_word": false
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"content": "</s_city>",
|
75 |
-
"lstrip": false,
|
76 |
-
"normalized": false,
|
77 |
-
"rstrip": false,
|
78 |
-
"single_word": false
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"content": "<s_mother_religion>",
|
82 |
-
"lstrip": false,
|
83 |
-
"normalized": false,
|
84 |
-
"rstrip": false,
|
85 |
-
"single_word": false
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"content": "</s_mother_nationality>",
|
89 |
-
"lstrip": false,
|
90 |
-
"normalized": false,
|
91 |
-
"rstrip": false,
|
92 |
-
"single_word": false
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"content": "<s_father_first_name>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"content": "<s_father_nationality>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": false,
|
106 |
-
"single_word": false
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"content": "<s_mother-nationality>",
|
110 |
"lstrip": false,
|
111 |
"normalized": false,
|
112 |
"rstrip": false,
|
113 |
"single_word": false
|
114 |
},
|
115 |
{
|
116 |
-
"content": "<
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
120 |
"single_word": false
|
121 |
},
|
122 |
{
|
123 |
-
"content": "<
|
124 |
"lstrip": false,
|
125 |
"normalized": false,
|
126 |
"rstrip": false,
|
127 |
"single_word": false
|
128 |
},
|
129 |
{
|
130 |
-
"content": "</
|
131 |
"lstrip": false,
|
132 |
"normalized": false,
|
133 |
"rstrip": false,
|
134 |
"single_word": false
|
135 |
},
|
136 |
{
|
137 |
-
"content": "
|
138 |
"lstrip": false,
|
139 |
"normalized": false,
|
140 |
"rstrip": false,
|
141 |
"single_word": false
|
142 |
},
|
143 |
{
|
144 |
-
"content": "
|
145 |
"lstrip": false,
|
146 |
"normalized": false,
|
147 |
"rstrip": false,
|
148 |
"single_word": false
|
149 |
},
|
150 |
{
|
151 |
-
"content": "<
|
152 |
"lstrip": false,
|
153 |
"normalized": false,
|
154 |
"rstrip": false,
|
155 |
"single_word": false
|
156 |
},
|
157 |
{
|
158 |
-
"content": "
|
159 |
"lstrip": false,
|
160 |
"normalized": false,
|
161 |
"rstrip": false,
|
162 |
"single_word": false
|
163 |
},
|
164 |
{
|
165 |
-
"content": "
|
166 |
"lstrip": false,
|
167 |
"normalized": false,
|
168 |
"rstrip": false,
|
169 |
"single_word": false
|
170 |
},
|
171 |
{
|
172 |
-
"content": "
|
173 |
"lstrip": false,
|
174 |
"normalized": false,
|
175 |
"rstrip": false,
|
176 |
"single_word": false
|
177 |
},
|
178 |
{
|
179 |
-
"content": "
|
180 |
"lstrip": false,
|
181 |
"normalized": false,
|
182 |
"rstrip": false,
|
183 |
"single_word": false
|
184 |
},
|
185 |
{
|
186 |
-
"content": "
|
187 |
"lstrip": false,
|
188 |
"normalized": false,
|
189 |
"rstrip": false,
|
@@ -197,196 +113,14 @@
|
|
197 |
"single_word": false
|
198 |
},
|
199 |
{
|
200 |
-
"content": "</
|
201 |
-
"lstrip": false,
|
202 |
-
"normalized": false,
|
203 |
-
"rstrip": false,
|
204 |
-
"single_word": false
|
205 |
-
},
|
206 |
-
{
|
207 |
-
"content": "</s_father_nationality>",
|
208 |
-
"lstrip": false,
|
209 |
-
"normalized": false,
|
210 |
-
"rstrip": false,
|
211 |
-
"single_word": false
|
212 |
-
},
|
213 |
-
{
|
214 |
-
"content": "</s_mother_age>",
|
215 |
-
"lstrip": false,
|
216 |
-
"normalized": false,
|
217 |
-
"rstrip": false,
|
218 |
-
"single_word": false
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"content": "</s_father_nationalty>",
|
222 |
-
"lstrip": false,
|
223 |
-
"normalized": false,
|
224 |
-
"rstrip": false,
|
225 |
-
"single_word": false
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"content": "</s_mother-nationality>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false
|
233 |
-
},
|
234 |
-
{
|
235 |
-
"content": "<s_child_first_name>",
|
236 |
-
"lstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"rstrip": false,
|
239 |
-
"single_word": false
|
240 |
-
},
|
241 |
-
{
|
242 |
-
"content": "</s_mother_middle_name>",
|
243 |
-
"lstrip": false,
|
244 |
-
"normalized": false,
|
245 |
-
"rstrip": false,
|
246 |
-
"single_word": false
|
247 |
-
},
|
248 |
-
{
|
249 |
-
"content": "<s_father_middle_name>",
|
250 |
-
"lstrip": false,
|
251 |
-
"normalized": false,
|
252 |
-
"rstrip": false,
|
253 |
-
"single_word": false
|
254 |
-
},
|
255 |
-
{
|
256 |
-
"content": "</s_father_race>",
|
257 |
-
"lstrip": false,
|
258 |
-
"normalized": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"single_word": false
|
261 |
-
},
|
262 |
-
{
|
263 |
-
"content": "<s_father_occupation>",
|
264 |
-
"lstrip": false,
|
265 |
-
"normalized": false,
|
266 |
-
"rstrip": false,
|
267 |
-
"single_word": false
|
268 |
-
},
|
269 |
-
{
|
270 |
-
"content": "</s_father_last_name>",
|
271 |
-
"lstrip": false,
|
272 |
-
"normalized": false,
|
273 |
-
"rstrip": false,
|
274 |
-
"single_word": false
|
275 |
-
},
|
276 |
-
{
|
277 |
-
"content": "</s_father_birthplace>",
|
278 |
-
"lstrip": false,
|
279 |
-
"normalized": false,
|
280 |
-
"rstrip": false,
|
281 |
-
"single_word": false
|
282 |
-
},
|
283 |
-
{
|
284 |
-
"content": "<s_father_religion>",
|
285 |
-
"lstrip": false,
|
286 |
-
"normalized": false,
|
287 |
-
"rstrip": false,
|
288 |
-
"single_word": false
|
289 |
-
},
|
290 |
-
{
|
291 |
-
"content": "</s_child_middle_name>",
|
292 |
-
"lstrip": false,
|
293 |
-
"normalized": false,
|
294 |
-
"rstrip": false,
|
295 |
-
"single_word": false
|
296 |
-
},
|
297 |
-
{
|
298 |
-
"content": "</s_mother_nationalty>",
|
299 |
-
"lstrip": false,
|
300 |
-
"normalized": false,
|
301 |
-
"rstrip": false,
|
302 |
-
"single_word": false
|
303 |
-
},
|
304 |
-
{
|
305 |
-
"content": "<s_mother_age>",
|
306 |
-
"lstrip": false,
|
307 |
-
"normalized": false,
|
308 |
-
"rstrip": false,
|
309 |
-
"single_word": false
|
310 |
-
},
|
311 |
-
{
|
312 |
-
"content": "</s>",
|
313 |
-
"lstrip": false,
|
314 |
-
"normalized": false,
|
315 |
-
"rstrip": false,
|
316 |
-
"single_word": false
|
317 |
-
},
|
318 |
-
{
|
319 |
-
"content": "</s_father_occupaation>",
|
320 |
-
"lstrip": false,
|
321 |
-
"normalized": false,
|
322 |
-
"rstrip": false,
|
323 |
-
"single_word": false
|
324 |
-
},
|
325 |
-
{
|
326 |
-
"content": "<s_mother_nationalty>",
|
327 |
-
"lstrip": false,
|
328 |
-
"normalized": false,
|
329 |
-
"rstrip": false,
|
330 |
-
"single_word": false
|
331 |
-
},
|
332 |
-
{
|
333 |
-
"content": "</s_DOB>",
|
334 |
-
"lstrip": false,
|
335 |
-
"normalized": false,
|
336 |
-
"rstrip": false,
|
337 |
-
"single_word": false
|
338 |
-
},
|
339 |
-
{
|
340 |
-
"content": "<s_father_nationalty>",
|
341 |
-
"lstrip": false,
|
342 |
-
"normalized": false,
|
343 |
-
"rstrip": false,
|
344 |
-
"single_word": false
|
345 |
-
},
|
346 |
-
{
|
347 |
-
"content": "<s_mother_first_name>",
|
348 |
-
"lstrip": false,
|
349 |
-
"normalized": false,
|
350 |
-
"rstrip": false,
|
351 |
-
"single_word": false
|
352 |
-
},
|
353 |
-
{
|
354 |
-
"content": "<s_father_birthplace>",
|
355 |
-
"lstrip": false,
|
356 |
-
"normalized": false,
|
357 |
-
"rstrip": false,
|
358 |
-
"single_word": false
|
359 |
-
},
|
360 |
-
{
|
361 |
-
"content": "</s_child_last_name>",
|
362 |
-
"lstrip": false,
|
363 |
-
"normalized": false,
|
364 |
-
"rstrip": false,
|
365 |
-
"single_word": false
|
366 |
-
},
|
367 |
-
{
|
368 |
-
"content": "</s_mother_religion>",
|
369 |
-
"lstrip": false,
|
370 |
-
"normalized": false,
|
371 |
-
"rstrip": false,
|
372 |
-
"single_word": false
|
373 |
-
},
|
374 |
-
{
|
375 |
-
"content": "</s_province>",
|
376 |
-
"lstrip": false,
|
377 |
-
"normalized": false,
|
378 |
-
"rstrip": false,
|
379 |
-
"single_word": false
|
380 |
-
},
|
381 |
-
{
|
382 |
-
"content": "<s_father_age>",
|
383 |
"lstrip": false,
|
384 |
"normalized": false,
|
385 |
"rstrip": false,
|
386 |
"single_word": false
|
387 |
},
|
388 |
{
|
389 |
-
"content": "</
|
390 |
"lstrip": false,
|
391 |
"normalized": false,
|
392 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
{
|
4 |
+
"content": "<s_mother_name>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
10 |
{
|
11 |
+
"content": "<s_father_name>",
|
12 |
"lstrip": false,
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
},
|
17 |
{
|
18 |
+
"content": "<s_first_name>",
|
19 |
"lstrip": false,
|
20 |
"normalized": false,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
{
|
25 |
+
"content": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"lstrip": false,
|
27 |
"normalized": false,
|
28 |
"rstrip": false,
|
29 |
"single_word": false
|
30 |
},
|
31 |
{
|
32 |
+
"content": "<s_random_number>",
|
33 |
"lstrip": false,
|
34 |
"normalized": false,
|
35 |
"rstrip": false,
|
36 |
"single_word": false
|
37 |
},
|
38 |
{
|
39 |
+
"content": "<s_place_of_birth>",
|
40 |
"lstrip": false,
|
41 |
"normalized": false,
|
42 |
"rstrip": false,
|
43 |
"single_word": false
|
44 |
},
|
45 |
{
|
46 |
+
"content": "</s_address>",
|
47 |
"lstrip": false,
|
48 |
"normalized": false,
|
49 |
"rstrip": false,
|
50 |
"single_word": false
|
51 |
},
|
52 |
{
|
53 |
+
"content": "</s_mother_name>",
|
54 |
"lstrip": false,
|
55 |
"normalized": false,
|
56 |
"rstrip": false,
|
57 |
"single_word": false
|
58 |
},
|
59 |
{
|
60 |
+
"content": "</s_random_number>",
|
61 |
"lstrip": false,
|
62 |
"normalized": false,
|
63 |
"rstrip": false,
|
64 |
"single_word": false
|
65 |
},
|
66 |
{
|
67 |
+
"content": "<s_title>",
|
68 |
"lstrip": false,
|
69 |
"normalized": false,
|
70 |
"rstrip": false,
|
71 |
"single_word": false
|
72 |
},
|
73 |
{
|
74 |
+
"content": "</s_first_name>",
|
75 |
"lstrip": false,
|
76 |
"normalized": false,
|
77 |
"rstrip": false,
|
78 |
"single_word": false
|
79 |
},
|
80 |
{
|
81 |
+
"content": "<s_last_name>",
|
82 |
"lstrip": false,
|
83 |
"normalized": false,
|
84 |
"rstrip": false,
|
85 |
"single_word": false
|
86 |
},
|
87 |
{
|
88 |
+
"content": "</s_title>",
|
89 |
"lstrip": false,
|
90 |
"normalized": false,
|
91 |
"rstrip": false,
|
92 |
"single_word": false
|
93 |
},
|
94 |
{
|
95 |
+
"content": "</s_father_name>",
|
96 |
"lstrip": false,
|
97 |
"normalized": false,
|
98 |
"rstrip": false,
|
99 |
"single_word": false
|
100 |
},
|
101 |
{
|
102 |
+
"content": "<s_address>",
|
103 |
"lstrip": false,
|
104 |
"normalized": false,
|
105 |
"rstrip": false,
|
|
|
113 |
"single_word": false
|
114 |
},
|
115 |
{
|
116 |
+
"content": "</s_last_name>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
120 |
"single_word": false
|
121 |
},
|
122 |
{
|
123 |
+
"content": "</s_place_of_birth>",
|
124 |
"lstrip": false,
|
125 |
"normalized": false,
|
126 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -91,7 +91,7 @@
|
|
91 |
},
|
92 |
{
|
93 |
"id": 57525,
|
94 |
-
"content": "<
|
95 |
"single_word": false,
|
96 |
"lstrip": false,
|
97 |
"rstrip": false,
|
@@ -100,7 +100,7 @@
|
|
100 |
},
|
101 |
{
|
102 |
"id": 57526,
|
103 |
-
"content": "<
|
104 |
"single_word": false,
|
105 |
"lstrip": false,
|
106 |
"rstrip": false,
|
@@ -109,7 +109,7 @@
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
112 |
-
"content": "<
|
113 |
"single_word": false,
|
114 |
"lstrip": false,
|
115 |
"rstrip": false,
|
@@ -118,7 +118,7 @@
|
|
118 |
},
|
119 |
{
|
120 |
"id": 57528,
|
121 |
-
"content": "
|
122 |
"single_word": false,
|
123 |
"lstrip": false,
|
124 |
"rstrip": false,
|
@@ -127,7 +127,7 @@
|
|
127 |
},
|
128 |
{
|
129 |
"id": 57529,
|
130 |
-
"content": "<
|
131 |
"single_word": false,
|
132 |
"lstrip": false,
|
133 |
"rstrip": false,
|
@@ -136,7 +136,7 @@
|
|
136 |
},
|
137 |
{
|
138 |
"id": 57530,
|
139 |
-
"content": "</
|
140 |
"single_word": false,
|
141 |
"lstrip": false,
|
142 |
"rstrip": false,
|
@@ -145,7 +145,7 @@
|
|
145 |
},
|
146 |
{
|
147 |
"id": 57531,
|
148 |
-
"content": "</
|
149 |
"single_word": false,
|
150 |
"lstrip": false,
|
151 |
"rstrip": false,
|
@@ -154,7 +154,7 @@
|
|
154 |
},
|
155 |
{
|
156 |
"id": 57532,
|
157 |
-
"content": "</
|
158 |
"single_word": false,
|
159 |
"lstrip": false,
|
160 |
"rstrip": false,
|
@@ -163,7 +163,7 @@
|
|
163 |
},
|
164 |
{
|
165 |
"id": 57533,
|
166 |
-
"content": "<
|
167 |
"single_word": false,
|
168 |
"lstrip": false,
|
169 |
"rstrip": false,
|
@@ -172,7 +172,7 @@
|
|
172 |
},
|
173 |
{
|
174 |
"id": 57534,
|
175 |
-
"content": "</
|
176 |
"single_word": false,
|
177 |
"lstrip": false,
|
178 |
"rstrip": false,
|
@@ -181,7 +181,7 @@
|
|
181 |
},
|
182 |
{
|
183 |
"id": 57535,
|
184 |
-
"content": "
|
185 |
"single_word": false,
|
186 |
"lstrip": false,
|
187 |
"rstrip": false,
|
@@ -190,7 +190,7 @@
|
|
190 |
},
|
191 |
{
|
192 |
"id": 57536,
|
193 |
-
"content": "
|
194 |
"single_word": false,
|
195 |
"lstrip": false,
|
196 |
"rstrip": false,
|
@@ -199,7 +199,7 @@
|
|
199 |
},
|
200 |
{
|
201 |
"id": 57537,
|
202 |
-
"content": "</
|
203 |
"single_word": false,
|
204 |
"lstrip": false,
|
205 |
"rstrip": false,
|
@@ -208,7 +208,7 @@
|
|
208 |
},
|
209 |
{
|
210 |
"id": 57538,
|
211 |
-
"content": "<
|
212 |
"single_word": false,
|
213 |
"lstrip": false,
|
214 |
"rstrip": false,
|
@@ -217,7 +217,7 @@
|
|
217 |
},
|
218 |
{
|
219 |
"id": 57539,
|
220 |
-
"content": "
|
221 |
"single_word": false,
|
222 |
"lstrip": false,
|
223 |
"rstrip": false,
|
@@ -226,349 +226,7 @@
|
|
226 |
},
|
227 |
{
|
228 |
"id": 57540,
|
229 |
-
"content": "
|
230 |
-
"single_word": false,
|
231 |
-
"lstrip": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"normalized": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"id": 57541,
|
238 |
-
"content": "<s_father_occupaation>",
|
239 |
-
"single_word": false,
|
240 |
-
"lstrip": false,
|
241 |
-
"rstrip": false,
|
242 |
-
"normalized": false,
|
243 |
-
"special": true
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"id": 57542,
|
247 |
-
"content": "<s_mother_middle_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_father_age>",
|
257 |
-
"single_word": false,
|
258 |
-
"lstrip": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"normalized": false,
|
261 |
-
"special": true
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"id": 57544,
|
265 |
-
"content": "<s_child_last_name>",
|
266 |
-
"single_word": false,
|
267 |
-
"lstrip": false,
|
268 |
-
"rstrip": false,
|
269 |
-
"normalized": false,
|
270 |
-
"special": true
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"id": 57545,
|
274 |
-
"content": "<s_child_middle_name>",
|
275 |
-
"single_word": false,
|
276 |
-
"lstrip": false,
|
277 |
-
"rstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"special": true
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"id": 57546,
|
283 |
-
"content": "<s_DOB>",
|
284 |
-
"single_word": false,
|
285 |
-
"lstrip": false,
|
286 |
-
"rstrip": false,
|
287 |
-
"normalized": false,
|
288 |
-
"special": true
|
289 |
-
},
|
290 |
-
{
|
291 |
-
"id": 57547,
|
292 |
-
"content": "<s_mother_birthplace>",
|
293 |
-
"single_word": false,
|
294 |
-
"lstrip": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"normalized": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"id": 57548,
|
301 |
-
"content": "</s_mother_last_name>",
|
302 |
-
"single_word": false,
|
303 |
-
"lstrip": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"normalized": false,
|
306 |
-
"special": true
|
307 |
-
},
|
308 |
-
{
|
309 |
-
"id": 57549,
|
310 |
-
"content": "<s_father_race>",
|
311 |
-
"single_word": false,
|
312 |
-
"lstrip": false,
|
313 |
-
"rstrip": false,
|
314 |
-
"normalized": false,
|
315 |
-
"special": true
|
316 |
-
},
|
317 |
-
{
|
318 |
-
"id": 57550,
|
319 |
-
"content": "<s_city>",
|
320 |
-
"single_word": false,
|
321 |
-
"lstrip": false,
|
322 |
-
"rstrip": false,
|
323 |
-
"normalized": false,
|
324 |
-
"special": true
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"id": 57551,
|
328 |
-
"content": "</s_mother_first_name>",
|
329 |
-
"single_word": false,
|
330 |
-
"lstrip": false,
|
331 |
-
"rstrip": false,
|
332 |
-
"normalized": false,
|
333 |
-
"special": true
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"id": 57552,
|
337 |
-
"content": "</s_mother_birthplace>",
|
338 |
-
"single_word": false,
|
339 |
-
"lstrip": false,
|
340 |
-
"rstrip": false,
|
341 |
-
"normalized": false,
|
342 |
-
"special": true
|
343 |
-
},
|
344 |
-
{
|
345 |
-
"id": 57553,
|
346 |
-
"content": "</s_father_nationality>",
|
347 |
-
"single_word": false,
|
348 |
-
"lstrip": false,
|
349 |
-
"rstrip": false,
|
350 |
-
"normalized": false,
|
351 |
-
"special": true
|
352 |
-
},
|
353 |
-
{
|
354 |
-
"id": 57554,
|
355 |
-
"content": "</s_mother_age>",
|
356 |
-
"single_word": false,
|
357 |
-
"lstrip": false,
|
358 |
-
"rstrip": false,
|
359 |
-
"normalized": false,
|
360 |
-
"special": true
|
361 |
-
},
|
362 |
-
{
|
363 |
-
"id": 57555,
|
364 |
-
"content": "</s_father_nationalty>",
|
365 |
-
"single_word": false,
|
366 |
-
"lstrip": false,
|
367 |
-
"rstrip": false,
|
368 |
-
"normalized": false,
|
369 |
-
"special": true
|
370 |
-
},
|
371 |
-
{
|
372 |
-
"id": 57556,
|
373 |
-
"content": "</s_mother-nationality>",
|
374 |
-
"single_word": false,
|
375 |
-
"lstrip": false,
|
376 |
-
"rstrip": false,
|
377 |
-
"normalized": false,
|
378 |
-
"special": true
|
379 |
-
},
|
380 |
-
{
|
381 |
-
"id": 57557,
|
382 |
-
"content": "<s_child_first_name>",
|
383 |
-
"single_word": false,
|
384 |
-
"lstrip": false,
|
385 |
-
"rstrip": false,
|
386 |
-
"normalized": false,
|
387 |
-
"special": true
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"id": 57558,
|
391 |
-
"content": "</s_mother_middle_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_father_middle_name>",
|
401 |
-
"single_word": false,
|
402 |
-
"lstrip": false,
|
403 |
-
"rstrip": false,
|
404 |
-
"normalized": false,
|
405 |
-
"special": true
|
406 |
-
},
|
407 |
-
{
|
408 |
-
"id": 57560,
|
409 |
-
"content": "</s_father_race>",
|
410 |
-
"single_word": false,
|
411 |
-
"lstrip": false,
|
412 |
-
"rstrip": false,
|
413 |
-
"normalized": false,
|
414 |
-
"special": true
|
415 |
-
},
|
416 |
-
{
|
417 |
-
"id": 57561,
|
418 |
-
"content": "<s_father_occupation>",
|
419 |
-
"single_word": false,
|
420 |
-
"lstrip": false,
|
421 |
-
"rstrip": false,
|
422 |
-
"normalized": false,
|
423 |
-
"special": true
|
424 |
-
},
|
425 |
-
{
|
426 |
-
"id": 57562,
|
427 |
-
"content": "</s_father_last_name>",
|
428 |
-
"single_word": false,
|
429 |
-
"lstrip": false,
|
430 |
-
"rstrip": false,
|
431 |
-
"normalized": false,
|
432 |
-
"special": true
|
433 |
-
},
|
434 |
-
{
|
435 |
-
"id": 57563,
|
436 |
-
"content": "</s_father_birthplace>",
|
437 |
-
"single_word": false,
|
438 |
-
"lstrip": false,
|
439 |
-
"rstrip": false,
|
440 |
-
"normalized": false,
|
441 |
-
"special": true
|
442 |
-
},
|
443 |
-
{
|
444 |
-
"id": 57564,
|
445 |
-
"content": "<s_father_religion>",
|
446 |
-
"single_word": false,
|
447 |
-
"lstrip": false,
|
448 |
-
"rstrip": false,
|
449 |
-
"normalized": false,
|
450 |
-
"special": true
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"id": 57565,
|
454 |
-
"content": "</s_child_middle_name>",
|
455 |
-
"single_word": false,
|
456 |
-
"lstrip": false,
|
457 |
-
"rstrip": false,
|
458 |
-
"normalized": false,
|
459 |
-
"special": true
|
460 |
-
},
|
461 |
-
{
|
462 |
-
"id": 57566,
|
463 |
-
"content": "</s_mother_nationalty>",
|
464 |
-
"single_word": false,
|
465 |
-
"lstrip": false,
|
466 |
-
"rstrip": false,
|
467 |
-
"normalized": false,
|
468 |
-
"special": true
|
469 |
-
},
|
470 |
-
{
|
471 |
-
"id": 57567,
|
472 |
-
"content": "<s_mother_age>",
|
473 |
-
"single_word": false,
|
474 |
-
"lstrip": false,
|
475 |
-
"rstrip": false,
|
476 |
-
"normalized": false,
|
477 |
-
"special": true
|
478 |
-
},
|
479 |
-
{
|
480 |
-
"id": 57568,
|
481 |
-
"content": "</s_father_occupaation>",
|
482 |
-
"single_word": false,
|
483 |
-
"lstrip": false,
|
484 |
-
"rstrip": false,
|
485 |
-
"normalized": false,
|
486 |
-
"special": true
|
487 |
-
},
|
488 |
-
{
|
489 |
-
"id": 57569,
|
490 |
-
"content": "<s_mother_nationalty>",
|
491 |
-
"single_word": false,
|
492 |
-
"lstrip": false,
|
493 |
-
"rstrip": false,
|
494 |
-
"normalized": false,
|
495 |
-
"special": true
|
496 |
-
},
|
497 |
-
{
|
498 |
-
"id": 57570,
|
499 |
-
"content": "</s_DOB>",
|
500 |
-
"single_word": false,
|
501 |
-
"lstrip": false,
|
502 |
-
"rstrip": false,
|
503 |
-
"normalized": false,
|
504 |
-
"special": true
|
505 |
-
},
|
506 |
-
{
|
507 |
-
"id": 57571,
|
508 |
-
"content": "<s_father_nationalty>",
|
509 |
-
"single_word": false,
|
510 |
-
"lstrip": false,
|
511 |
-
"rstrip": false,
|
512 |
-
"normalized": false,
|
513 |
-
"special": true
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"id": 57572,
|
517 |
-
"content": "<s_mother_first_name>",
|
518 |
-
"single_word": false,
|
519 |
-
"lstrip": false,
|
520 |
-
"rstrip": false,
|
521 |
-
"normalized": false,
|
522 |
-
"special": true
|
523 |
-
},
|
524 |
-
{
|
525 |
-
"id": 57573,
|
526 |
-
"content": "<s_father_birthplace>",
|
527 |
-
"single_word": false,
|
528 |
-
"lstrip": false,
|
529 |
-
"rstrip": false,
|
530 |
-
"normalized": false,
|
531 |
-
"special": true
|
532 |
-
},
|
533 |
-
{
|
534 |
-
"id": 57574,
|
535 |
-
"content": "</s_child_last_name>",
|
536 |
-
"single_word": false,
|
537 |
-
"lstrip": false,
|
538 |
-
"rstrip": false,
|
539 |
-
"normalized": false,
|
540 |
-
"special": true
|
541 |
-
},
|
542 |
-
{
|
543 |
-
"id": 57575,
|
544 |
-
"content": "</s_mother_religion>",
|
545 |
-
"single_word": false,
|
546 |
-
"lstrip": false,
|
547 |
-
"rstrip": false,
|
548 |
-
"normalized": false,
|
549 |
-
"special": true
|
550 |
-
},
|
551 |
-
{
|
552 |
-
"id": 57576,
|
553 |
-
"content": "</s_province>",
|
554 |
-
"single_word": false,
|
555 |
-
"lstrip": false,
|
556 |
-
"rstrip": false,
|
557 |
-
"normalized": false,
|
558 |
-
"special": true
|
559 |
-
},
|
560 |
-
{
|
561 |
-
"id": 57577,
|
562 |
-
"content": "<s_father_age>",
|
563 |
-
"single_word": false,
|
564 |
-
"lstrip": false,
|
565 |
-
"rstrip": false,
|
566 |
-
"normalized": false,
|
567 |
-
"special": true
|
568 |
-
},
|
569 |
-
{
|
570 |
-
"id": 57578,
|
571 |
-
"content": "</s_father_middle_name>",
|
572 |
"single_word": false,
|
573 |
"lstrip": false,
|
574 |
"rstrip": false,
|
|
|
91 |
},
|
92 |
{
|
93 |
"id": 57525,
|
94 |
+
"content": "<s_mother_name>",
|
95 |
"single_word": false,
|
96 |
"lstrip": false,
|
97 |
"rstrip": false,
|
|
|
100 |
},
|
101 |
{
|
102 |
"id": 57526,
|
103 |
+
"content": "<s_father_name>",
|
104 |
"single_word": false,
|
105 |
"lstrip": false,
|
106 |
"rstrip": false,
|
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
112 |
+
"content": "<s_first_name>",
|
113 |
"single_word": false,
|
114 |
"lstrip": false,
|
115 |
"rstrip": false,
|
|
|
118 |
},
|
119 |
{
|
120 |
"id": 57528,
|
121 |
+
"content": "<s_random_number>",
|
122 |
"single_word": false,
|
123 |
"lstrip": false,
|
124 |
"rstrip": false,
|
|
|
127 |
},
|
128 |
{
|
129 |
"id": 57529,
|
130 |
+
"content": "<s_place_of_birth>",
|
131 |
"single_word": false,
|
132 |
"lstrip": false,
|
133 |
"rstrip": false,
|
|
|
136 |
},
|
137 |
{
|
138 |
"id": 57530,
|
139 |
+
"content": "</s_address>",
|
140 |
"single_word": false,
|
141 |
"lstrip": false,
|
142 |
"rstrip": false,
|
|
|
145 |
},
|
146 |
{
|
147 |
"id": 57531,
|
148 |
+
"content": "</s_mother_name>",
|
149 |
"single_word": false,
|
150 |
"lstrip": false,
|
151 |
"rstrip": false,
|
|
|
154 |
},
|
155 |
{
|
156 |
"id": 57532,
|
157 |
+
"content": "</s_random_number>",
|
158 |
"single_word": false,
|
159 |
"lstrip": false,
|
160 |
"rstrip": false,
|
|
|
163 |
},
|
164 |
{
|
165 |
"id": 57533,
|
166 |
+
"content": "<s_title>",
|
167 |
"single_word": false,
|
168 |
"lstrip": false,
|
169 |
"rstrip": false,
|
|
|
172 |
},
|
173 |
{
|
174 |
"id": 57534,
|
175 |
+
"content": "</s_first_name>",
|
176 |
"single_word": false,
|
177 |
"lstrip": false,
|
178 |
"rstrip": false,
|
|
|
181 |
},
|
182 |
{
|
183 |
"id": 57535,
|
184 |
+
"content": "<s_last_name>",
|
185 |
"single_word": false,
|
186 |
"lstrip": false,
|
187 |
"rstrip": false,
|
|
|
190 |
},
|
191 |
{
|
192 |
"id": 57536,
|
193 |
+
"content": "</s_title>",
|
194 |
"single_word": false,
|
195 |
"lstrip": false,
|
196 |
"rstrip": false,
|
|
|
199 |
},
|
200 |
{
|
201 |
"id": 57537,
|
202 |
+
"content": "</s_father_name>",
|
203 |
"single_word": false,
|
204 |
"lstrip": false,
|
205 |
"rstrip": false,
|
|
|
208 |
},
|
209 |
{
|
210 |
"id": 57538,
|
211 |
+
"content": "<s_address>",
|
212 |
"single_word": false,
|
213 |
"lstrip": false,
|
214 |
"rstrip": false,
|
|
|
217 |
},
|
218 |
{
|
219 |
"id": 57539,
|
220 |
+
"content": "</s_last_name>",
|
221 |
"single_word": false,
|
222 |
"lstrip": false,
|
223 |
"rstrip": false,
|
|
|
226 |
},
|
227 |
{
|
228 |
"id": 57540,
|
229 |
+
"content": "</s_place_of_birth>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
"single_word": false,
|
231 |
"lstrip": false,
|
232 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -65,7 +65,7 @@
|
|
65 |
"special": true
|
66 |
},
|
67 |
"57525": {
|
68 |
-
"content": "<
|
69 |
"lstrip": false,
|
70 |
"normalized": false,
|
71 |
"rstrip": false,
|
@@ -73,7 +73,7 @@
|
|
73 |
"special": true
|
74 |
},
|
75 |
"57526": {
|
76 |
-
"content": "<
|
77 |
"lstrip": false,
|
78 |
"normalized": false,
|
79 |
"rstrip": false,
|
@@ -81,7 +81,7 @@
|
|
81 |
"special": true
|
82 |
},
|
83 |
"57527": {
|
84 |
-
"content": "<
|
85 |
"lstrip": false,
|
86 |
"normalized": false,
|
87 |
"rstrip": false,
|
@@ -89,7 +89,7 @@
|
|
89 |
"special": true
|
90 |
},
|
91 |
"57528": {
|
92 |
-
"content": "
|
93 |
"lstrip": false,
|
94 |
"normalized": false,
|
95 |
"rstrip": false,
|
@@ -97,7 +97,7 @@
|
|
97 |
"special": true
|
98 |
},
|
99 |
"57529": {
|
100 |
-
"content": "<
|
101 |
"lstrip": false,
|
102 |
"normalized": false,
|
103 |
"rstrip": false,
|
@@ -105,7 +105,7 @@
|
|
105 |
"special": true
|
106 |
},
|
107 |
"57530": {
|
108 |
-
"content": "</
|
109 |
"lstrip": false,
|
110 |
"normalized": false,
|
111 |
"rstrip": false,
|
@@ -113,7 +113,7 @@
|
|
113 |
"special": true
|
114 |
},
|
115 |
"57531": {
|
116 |
-
"content": "</
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
@@ -121,7 +121,7 @@
|
|
121 |
"special": true
|
122 |
},
|
123 |
"57532": {
|
124 |
-
"content": "</
|
125 |
"lstrip": false,
|
126 |
"normalized": false,
|
127 |
"rstrip": false,
|
@@ -129,7 +129,7 @@
|
|
129 |
"special": true
|
130 |
},
|
131 |
"57533": {
|
132 |
-
"content": "<
|
133 |
"lstrip": false,
|
134 |
"normalized": false,
|
135 |
"rstrip": false,
|
@@ -137,7 +137,7 @@
|
|
137 |
"special": true
|
138 |
},
|
139 |
"57534": {
|
140 |
-
"content": "</
|
141 |
"lstrip": false,
|
142 |
"normalized": false,
|
143 |
"rstrip": false,
|
@@ -145,7 +145,7 @@
|
|
145 |
"special": true
|
146 |
},
|
147 |
"57535": {
|
148 |
-
"content": "
|
149 |
"lstrip": false,
|
150 |
"normalized": false,
|
151 |
"rstrip": false,
|
@@ -153,7 +153,7 @@
|
|
153 |
"special": true
|
154 |
},
|
155 |
"57536": {
|
156 |
-
"content": "
|
157 |
"lstrip": false,
|
158 |
"normalized": false,
|
159 |
"rstrip": false,
|
@@ -161,7 +161,7 @@
|
|
161 |
"special": true
|
162 |
},
|
163 |
"57537": {
|
164 |
-
"content": "</
|
165 |
"lstrip": false,
|
166 |
"normalized": false,
|
167 |
"rstrip": false,
|
@@ -169,7 +169,7 @@
|
|
169 |
"special": true
|
170 |
},
|
171 |
"57538": {
|
172 |
-
"content": "<
|
173 |
"lstrip": false,
|
174 |
"normalized": false,
|
175 |
"rstrip": false,
|
@@ -177,7 +177,7 @@
|
|
177 |
"special": true
|
178 |
},
|
179 |
"57539": {
|
180 |
-
"content": "
|
181 |
"lstrip": false,
|
182 |
"normalized": false,
|
183 |
"rstrip": false,
|
@@ -185,311 +185,7 @@
|
|
185 |
"special": true
|
186 |
},
|
187 |
"57540": {
|
188 |
-
"content": "
|
189 |
-
"lstrip": false,
|
190 |
-
"normalized": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"single_word": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
"57541": {
|
196 |
-
"content": "<s_father_occupaation>",
|
197 |
-
"lstrip": false,
|
198 |
-
"normalized": false,
|
199 |
-
"rstrip": false,
|
200 |
-
"single_word": false,
|
201 |
-
"special": true
|
202 |
-
},
|
203 |
-
"57542": {
|
204 |
-
"content": "<s_mother_middle_name>",
|
205 |
-
"lstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"rstrip": false,
|
208 |
-
"single_word": false,
|
209 |
-
"special": true
|
210 |
-
},
|
211 |
-
"57543": {
|
212 |
-
"content": "</s_father_age>",
|
213 |
-
"lstrip": false,
|
214 |
-
"normalized": false,
|
215 |
-
"rstrip": false,
|
216 |
-
"single_word": false,
|
217 |
-
"special": true
|
218 |
-
},
|
219 |
-
"57544": {
|
220 |
-
"content": "<s_child_last_name>",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
"57545": {
|
228 |
-
"content": "<s_child_middle_name>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": true
|
234 |
-
},
|
235 |
-
"57546": {
|
236 |
-
"content": "<s_DOB>",
|
237 |
-
"lstrip": false,
|
238 |
-
"normalized": false,
|
239 |
-
"rstrip": false,
|
240 |
-
"single_word": false,
|
241 |
-
"special": true
|
242 |
-
},
|
243 |
-
"57547": {
|
244 |
-
"content": "<s_mother_birthplace>",
|
245 |
-
"lstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"rstrip": false,
|
248 |
-
"single_word": false,
|
249 |
-
"special": true
|
250 |
-
},
|
251 |
-
"57548": {
|
252 |
-
"content": "</s_mother_last_name>",
|
253 |
-
"lstrip": false,
|
254 |
-
"normalized": false,
|
255 |
-
"rstrip": false,
|
256 |
-
"single_word": false,
|
257 |
-
"special": true
|
258 |
-
},
|
259 |
-
"57549": {
|
260 |
-
"content": "<s_father_race>",
|
261 |
-
"lstrip": false,
|
262 |
-
"normalized": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"single_word": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
"57550": {
|
268 |
-
"content": "<s_city>",
|
269 |
-
"lstrip": false,
|
270 |
-
"normalized": false,
|
271 |
-
"rstrip": false,
|
272 |
-
"single_word": false,
|
273 |
-
"special": true
|
274 |
-
},
|
275 |
-
"57551": {
|
276 |
-
"content": "</s_mother_first_name>",
|
277 |
-
"lstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"rstrip": false,
|
280 |
-
"single_word": false,
|
281 |
-
"special": true
|
282 |
-
},
|
283 |
-
"57552": {
|
284 |
-
"content": "</s_mother_birthplace>",
|
285 |
-
"lstrip": false,
|
286 |
-
"normalized": false,
|
287 |
-
"rstrip": false,
|
288 |
-
"single_word": false,
|
289 |
-
"special": true
|
290 |
-
},
|
291 |
-
"57553": {
|
292 |
-
"content": "</s_father_nationality>",
|
293 |
-
"lstrip": false,
|
294 |
-
"normalized": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"single_word": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
"57554": {
|
300 |
-
"content": "</s_mother_age>",
|
301 |
-
"lstrip": false,
|
302 |
-
"normalized": false,
|
303 |
-
"rstrip": false,
|
304 |
-
"single_word": false,
|
305 |
-
"special": true
|
306 |
-
},
|
307 |
-
"57555": {
|
308 |
-
"content": "</s_father_nationalty>",
|
309 |
-
"lstrip": false,
|
310 |
-
"normalized": false,
|
311 |
-
"rstrip": false,
|
312 |
-
"single_word": false,
|
313 |
-
"special": true
|
314 |
-
},
|
315 |
-
"57556": {
|
316 |
-
"content": "</s_mother-nationality>",
|
317 |
-
"lstrip": false,
|
318 |
-
"normalized": false,
|
319 |
-
"rstrip": false,
|
320 |
-
"single_word": false,
|
321 |
-
"special": true
|
322 |
-
},
|
323 |
-
"57557": {
|
324 |
-
"content": "<s_child_first_name>",
|
325 |
-
"lstrip": false,
|
326 |
-
"normalized": false,
|
327 |
-
"rstrip": false,
|
328 |
-
"single_word": false,
|
329 |
-
"special": true
|
330 |
-
},
|
331 |
-
"57558": {
|
332 |
-
"content": "</s_mother_middle_name>",
|
333 |
-
"lstrip": false,
|
334 |
-
"normalized": false,
|
335 |
-
"rstrip": false,
|
336 |
-
"single_word": false,
|
337 |
-
"special": true
|
338 |
-
},
|
339 |
-
"57559": {
|
340 |
-
"content": "<s_father_middle_name>",
|
341 |
-
"lstrip": false,
|
342 |
-
"normalized": false,
|
343 |
-
"rstrip": false,
|
344 |
-
"single_word": false,
|
345 |
-
"special": true
|
346 |
-
},
|
347 |
-
"57560": {
|
348 |
-
"content": "</s_father_race>",
|
349 |
-
"lstrip": false,
|
350 |
-
"normalized": false,
|
351 |
-
"rstrip": false,
|
352 |
-
"single_word": false,
|
353 |
-
"special": true
|
354 |
-
},
|
355 |
-
"57561": {
|
356 |
-
"content": "<s_father_occupation>",
|
357 |
-
"lstrip": false,
|
358 |
-
"normalized": false,
|
359 |
-
"rstrip": false,
|
360 |
-
"single_word": false,
|
361 |
-
"special": true
|
362 |
-
},
|
363 |
-
"57562": {
|
364 |
-
"content": "</s_father_last_name>",
|
365 |
-
"lstrip": false,
|
366 |
-
"normalized": false,
|
367 |
-
"rstrip": false,
|
368 |
-
"single_word": false,
|
369 |
-
"special": true
|
370 |
-
},
|
371 |
-
"57563": {
|
372 |
-
"content": "</s_father_birthplace>",
|
373 |
-
"lstrip": false,
|
374 |
-
"normalized": false,
|
375 |
-
"rstrip": false,
|
376 |
-
"single_word": false,
|
377 |
-
"special": true
|
378 |
-
},
|
379 |
-
"57564": {
|
380 |
-
"content": "<s_father_religion>",
|
381 |
-
"lstrip": false,
|
382 |
-
"normalized": false,
|
383 |
-
"rstrip": false,
|
384 |
-
"single_word": false,
|
385 |
-
"special": true
|
386 |
-
},
|
387 |
-
"57565": {
|
388 |
-
"content": "</s_child_middle_name>",
|
389 |
-
"lstrip": false,
|
390 |
-
"normalized": false,
|
391 |
-
"rstrip": false,
|
392 |
-
"single_word": false,
|
393 |
-
"special": true
|
394 |
-
},
|
395 |
-
"57566": {
|
396 |
-
"content": "</s_mother_nationalty>",
|
397 |
-
"lstrip": false,
|
398 |
-
"normalized": false,
|
399 |
-
"rstrip": false,
|
400 |
-
"single_word": false,
|
401 |
-
"special": true
|
402 |
-
},
|
403 |
-
"57567": {
|
404 |
-
"content": "<s_mother_age>",
|
405 |
-
"lstrip": false,
|
406 |
-
"normalized": false,
|
407 |
-
"rstrip": false,
|
408 |
-
"single_word": false,
|
409 |
-
"special": true
|
410 |
-
},
|
411 |
-
"57568": {
|
412 |
-
"content": "</s_father_occupaation>",
|
413 |
-
"lstrip": false,
|
414 |
-
"normalized": false,
|
415 |
-
"rstrip": false,
|
416 |
-
"single_word": false,
|
417 |
-
"special": true
|
418 |
-
},
|
419 |
-
"57569": {
|
420 |
-
"content": "<s_mother_nationalty>",
|
421 |
-
"lstrip": false,
|
422 |
-
"normalized": false,
|
423 |
-
"rstrip": false,
|
424 |
-
"single_word": false,
|
425 |
-
"special": true
|
426 |
-
},
|
427 |
-
"57570": {
|
428 |
-
"content": "</s_DOB>",
|
429 |
-
"lstrip": false,
|
430 |
-
"normalized": false,
|
431 |
-
"rstrip": false,
|
432 |
-
"single_word": false,
|
433 |
-
"special": true
|
434 |
-
},
|
435 |
-
"57571": {
|
436 |
-
"content": "<s_father_nationalty>",
|
437 |
-
"lstrip": false,
|
438 |
-
"normalized": false,
|
439 |
-
"rstrip": false,
|
440 |
-
"single_word": false,
|
441 |
-
"special": true
|
442 |
-
},
|
443 |
-
"57572": {
|
444 |
-
"content": "<s_mother_first_name>",
|
445 |
-
"lstrip": false,
|
446 |
-
"normalized": false,
|
447 |
-
"rstrip": false,
|
448 |
-
"single_word": false,
|
449 |
-
"special": true
|
450 |
-
},
|
451 |
-
"57573": {
|
452 |
-
"content": "<s_father_birthplace>",
|
453 |
-
"lstrip": false,
|
454 |
-
"normalized": false,
|
455 |
-
"rstrip": false,
|
456 |
-
"single_word": false,
|
457 |
-
"special": true
|
458 |
-
},
|
459 |
-
"57574": {
|
460 |
-
"content": "</s_child_last_name>",
|
461 |
-
"lstrip": false,
|
462 |
-
"normalized": false,
|
463 |
-
"rstrip": false,
|
464 |
-
"single_word": false,
|
465 |
-
"special": true
|
466 |
-
},
|
467 |
-
"57575": {
|
468 |
-
"content": "</s_mother_religion>",
|
469 |
-
"lstrip": false,
|
470 |
-
"normalized": false,
|
471 |
-
"rstrip": false,
|
472 |
-
"single_word": false,
|
473 |
-
"special": true
|
474 |
-
},
|
475 |
-
"57576": {
|
476 |
-
"content": "</s_province>",
|
477 |
-
"lstrip": false,
|
478 |
-
"normalized": false,
|
479 |
-
"rstrip": false,
|
480 |
-
"single_word": false,
|
481 |
-
"special": true
|
482 |
-
},
|
483 |
-
"57577": {
|
484 |
-
"content": "<s_father_age>",
|
485 |
-
"lstrip": false,
|
486 |
-
"normalized": false,
|
487 |
-
"rstrip": false,
|
488 |
-
"single_word": false,
|
489 |
-
"special": true
|
490 |
-
},
|
491 |
-
"57578": {
|
492 |
-
"content": "</s_father_middle_name>",
|
493 |
"lstrip": false,
|
494 |
"normalized": false,
|
495 |
"rstrip": false,
|
@@ -498,62 +194,24 @@
|
|
498 |
}
|
499 |
},
|
500 |
"additional_special_tokens": [
|
501 |
-
"<
|
502 |
-
"<
|
503 |
-
"<
|
504 |
-
"</s_father_religion>",
|
505 |
-
"<s_mother_nationality>",
|
506 |
-
"</s_father_first_name>",
|
507 |
-
"</s_father_occupation>",
|
508 |
-
"</s_child_first_name>",
|
509 |
-
"<s_mother_race>",
|
510 |
-
"</s_mother_race>",
|
511 |
-
"</s_city>",
|
512 |
-
"<s_mother_religion>",
|
513 |
-
"</s_mother_nationality>",
|
514 |
-
"<s_father_first_name>",
|
515 |
-
"<s_father_nationality>",
|
516 |
-
"<s_mother-nationality>",
|
517 |
-
"<s_father_occupaation>",
|
518 |
-
"<s_mother_middle_name>",
|
519 |
-
"</s_father_age>",
|
520 |
-
"<s_child_last_name>",
|
521 |
-
"<s_child_middle_name>",
|
522 |
-
"<s_DOB>",
|
523 |
-
"<s_mother_birthplace>",
|
524 |
-
"</s_mother_last_name>",
|
525 |
-
"<s_father_race>",
|
526 |
-
"<s_city>",
|
527 |
-
"</s_mother_first_name>",
|
528 |
-
"<s>",
|
529 |
-
"</s_mother_birthplace>",
|
530 |
-
"</s_father_nationality>",
|
531 |
-
"</s_mother_age>",
|
532 |
-
"</s_father_nationalty>",
|
533 |
-
"</s_mother-nationality>",
|
534 |
-
"<s_child_first_name>",
|
535 |
-
"</s_mother_middle_name>",
|
536 |
-
"<s_father_middle_name>",
|
537 |
-
"</s_father_race>",
|
538 |
-
"<s_father_occupation>",
|
539 |
-
"</s_father_last_name>",
|
540 |
-
"</s_father_birthplace>",
|
541 |
-
"<s_father_religion>",
|
542 |
-
"</s_child_middle_name>",
|
543 |
-
"</s_mother_nationalty>",
|
544 |
-
"<s_mother_age>",
|
545 |
"</s>",
|
546 |
-
"
|
547 |
-
"<
|
548 |
-
"</
|
549 |
-
"
|
550 |
-
"
|
551 |
-
"<
|
552 |
-
"</
|
553 |
-
"
|
554 |
-
"</
|
555 |
-
"
|
556 |
-
"
|
|
|
|
|
|
|
557 |
],
|
558 |
"bos_token": "<s>",
|
559 |
"clean_up_tokenization_spaces": true,
|
|
|
65 |
"special": true
|
66 |
},
|
67 |
"57525": {
|
68 |
+
"content": "<s_mother_name>",
|
69 |
"lstrip": false,
|
70 |
"normalized": false,
|
71 |
"rstrip": false,
|
|
|
73 |
"special": true
|
74 |
},
|
75 |
"57526": {
|
76 |
+
"content": "<s_father_name>",
|
77 |
"lstrip": false,
|
78 |
"normalized": false,
|
79 |
"rstrip": false,
|
|
|
81 |
"special": true
|
82 |
},
|
83 |
"57527": {
|
84 |
+
"content": "<s_first_name>",
|
85 |
"lstrip": false,
|
86 |
"normalized": false,
|
87 |
"rstrip": false,
|
|
|
89 |
"special": true
|
90 |
},
|
91 |
"57528": {
|
92 |
+
"content": "<s_random_number>",
|
93 |
"lstrip": false,
|
94 |
"normalized": false,
|
95 |
"rstrip": false,
|
|
|
97 |
"special": true
|
98 |
},
|
99 |
"57529": {
|
100 |
+
"content": "<s_place_of_birth>",
|
101 |
"lstrip": false,
|
102 |
"normalized": false,
|
103 |
"rstrip": false,
|
|
|
105 |
"special": true
|
106 |
},
|
107 |
"57530": {
|
108 |
+
"content": "</s_address>",
|
109 |
"lstrip": false,
|
110 |
"normalized": false,
|
111 |
"rstrip": false,
|
|
|
113 |
"special": true
|
114 |
},
|
115 |
"57531": {
|
116 |
+
"content": "</s_mother_name>",
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
|
|
121 |
"special": true
|
122 |
},
|
123 |
"57532": {
|
124 |
+
"content": "</s_random_number>",
|
125 |
"lstrip": false,
|
126 |
"normalized": false,
|
127 |
"rstrip": false,
|
|
|
129 |
"special": true
|
130 |
},
|
131 |
"57533": {
|
132 |
+
"content": "<s_title>",
|
133 |
"lstrip": false,
|
134 |
"normalized": false,
|
135 |
"rstrip": false,
|
|
|
137 |
"special": true
|
138 |
},
|
139 |
"57534": {
|
140 |
+
"content": "</s_first_name>",
|
141 |
"lstrip": false,
|
142 |
"normalized": false,
|
143 |
"rstrip": false,
|
|
|
145 |
"special": true
|
146 |
},
|
147 |
"57535": {
|
148 |
+
"content": "<s_last_name>",
|
149 |
"lstrip": false,
|
150 |
"normalized": false,
|
151 |
"rstrip": false,
|
|
|
153 |
"special": true
|
154 |
},
|
155 |
"57536": {
|
156 |
+
"content": "</s_title>",
|
157 |
"lstrip": false,
|
158 |
"normalized": false,
|
159 |
"rstrip": false,
|
|
|
161 |
"special": true
|
162 |
},
|
163 |
"57537": {
|
164 |
+
"content": "</s_father_name>",
|
165 |
"lstrip": false,
|
166 |
"normalized": false,
|
167 |
"rstrip": false,
|
|
|
169 |
"special": true
|
170 |
},
|
171 |
"57538": {
|
172 |
+
"content": "<s_address>",
|
173 |
"lstrip": false,
|
174 |
"normalized": false,
|
175 |
"rstrip": false,
|
|
|
177 |
"special": true
|
178 |
},
|
179 |
"57539": {
|
180 |
+
"content": "</s_last_name>",
|
181 |
"lstrip": false,
|
182 |
"normalized": false,
|
183 |
"rstrip": false,
|
|
|
185 |
"special": true
|
186 |
},
|
187 |
"57540": {
|
188 |
+
"content": "</s_place_of_birth>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
"lstrip": false,
|
190 |
"normalized": false,
|
191 |
"rstrip": false,
|
|
|
194 |
}
|
195 |
},
|
196 |
"additional_special_tokens": [
|
197 |
+
"<s_mother_name>",
|
198 |
+
"<s_father_name>",
|
199 |
+
"<s_first_name>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
"</s>",
|
201 |
+
"<s_random_number>",
|
202 |
+
"<s_place_of_birth>",
|
203 |
+
"</s_address>",
|
204 |
+
"</s_mother_name>",
|
205 |
+
"</s_random_number>",
|
206 |
+
"<s_title>",
|
207 |
+
"</s_first_name>",
|
208 |
+
"<s_last_name>",
|
209 |
+
"</s_title>",
|
210 |
+
"</s_father_name>",
|
211 |
+
"<s_address>",
|
212 |
+
"<s>",
|
213 |
+
"</s_last_name>",
|
214 |
+
"</s_place_of_birth>"
|
215 |
],
|
216 |
"bos_token": "<s>",
|
217 |
"clean_up_tokenization_spaces": true,
|