Commit
·
289b4e9
1
Parent(s):
862d120
Training in progress, epoch 0
Browse files- added_tokens.json +14 -14
- tokenizer.json +14 -14
added_tokens.json
CHANGED
@@ -4,36 +4,36 @@
|
|
4 |
"</s_1_familiya>": 35067,
|
5 |
"</s_1_imya>": 35069,
|
6 |
"</s_1_kod_podrazdeleniya>": 35065,
|
7 |
-
"</s_1_mashinnyj_tekst_1>":
|
8 |
-
"</s_1_mashinnyj_tekst_2>":
|
9 |
"</s_1_mesto_rozhdeniya1>": 35077,
|
10 |
-
"</s_1_mesto_rozhdeniya2>":
|
11 |
-
"</s_1_mesto_rozhdeniya3>":
|
12 |
"</s_1_otchestvo>": 35071,
|
13 |
"</s_1_pasport_vydan1>": 35057,
|
14 |
"</s_1_pasport_vydan2>": 35061,
|
15 |
-
"</s_1_pasport_vydan3>":
|
16 |
"</s_1_pol>": 35073,
|
17 |
-
"</s_1_seriya_nomer_1>":
|
18 |
-
"</s_1_seriya_nomer_2>":
|
19 |
"</s_name>": 35059,
|
20 |
"<s_1_data_rozhdeniya>": 35074,
|
21 |
"<s_1_data_vydachi>": 35062,
|
22 |
"<s_1_familiya>": 35066,
|
23 |
"<s_1_imya>": 35068,
|
24 |
"<s_1_kod_podrazdeleniya>": 35064,
|
25 |
-
"<s_1_mashinnyj_tekst_1>":
|
26 |
-
"<s_1_mashinnyj_tekst_2>":
|
27 |
"<s_1_mesto_rozhdeniya1>": 35076,
|
28 |
-
"<s_1_mesto_rozhdeniya2>":
|
29 |
-
"<s_1_mesto_rozhdeniya3>":
|
30 |
"<s_1_otchestvo>": 35070,
|
31 |
"<s_1_pasport_vydan1>": 35056,
|
32 |
"<s_1_pasport_vydan2>": 35060,
|
33 |
-
"<s_1_pasport_vydan3>":
|
34 |
"<s_1_pol>": 35072,
|
35 |
-
"<s_1_seriya_nomer_1>":
|
36 |
-
"<s_1_seriya_nomer_2>":
|
37 |
"<s_500k>": 35054,
|
38 |
"<s_a4>": 35092,
|
39 |
"<s_donut_rus>": 35055,
|
|
|
4 |
"</s_1_familiya>": 35067,
|
5 |
"</s_1_imya>": 35069,
|
6 |
"</s_1_kod_podrazdeleniya>": 35065,
|
7 |
+
"</s_1_mashinnyj_tekst_1>": 35087,
|
8 |
+
"</s_1_mashinnyj_tekst_2>": 35089,
|
9 |
"</s_1_mesto_rozhdeniya1>": 35077,
|
10 |
+
"</s_1_mesto_rozhdeniya2>": 35085,
|
11 |
+
"</s_1_mesto_rozhdeniya3>": 35091,
|
12 |
"</s_1_otchestvo>": 35071,
|
13 |
"</s_1_pasport_vydan1>": 35057,
|
14 |
"</s_1_pasport_vydan2>": 35061,
|
15 |
+
"</s_1_pasport_vydan3>": 35083,
|
16 |
"</s_1_pol>": 35073,
|
17 |
+
"</s_1_seriya_nomer_1>": 35079,
|
18 |
+
"</s_1_seriya_nomer_2>": 35081,
|
19 |
"</s_name>": 35059,
|
20 |
"<s_1_data_rozhdeniya>": 35074,
|
21 |
"<s_1_data_vydachi>": 35062,
|
22 |
"<s_1_familiya>": 35066,
|
23 |
"<s_1_imya>": 35068,
|
24 |
"<s_1_kod_podrazdeleniya>": 35064,
|
25 |
+
"<s_1_mashinnyj_tekst_1>": 35086,
|
26 |
+
"<s_1_mashinnyj_tekst_2>": 35088,
|
27 |
"<s_1_mesto_rozhdeniya1>": 35076,
|
28 |
+
"<s_1_mesto_rozhdeniya2>": 35084,
|
29 |
+
"<s_1_mesto_rozhdeniya3>": 35090,
|
30 |
"<s_1_otchestvo>": 35070,
|
31 |
"<s_1_pasport_vydan1>": 35056,
|
32 |
"<s_1_pasport_vydan2>": 35060,
|
33 |
+
"<s_1_pasport_vydan3>": 35082,
|
34 |
"<s_1_pol>": 35072,
|
35 |
+
"<s_1_seriya_nomer_1>": 35078,
|
36 |
+
"<s_1_seriya_nomer_2>": 35080,
|
37 |
"<s_500k>": 35054,
|
38 |
"<s_a4>": 35092,
|
39 |
"<s_donut_rus>": 35055,
|
tokenizer.json
CHANGED
@@ -266,7 +266,7 @@
|
|
266 |
},
|
267 |
{
|
268 |
"id": 35078,
|
269 |
-
"content": "<
|
270 |
"single_word": false,
|
271 |
"lstrip": false,
|
272 |
"rstrip": false,
|
@@ -275,7 +275,7 @@
|
|
275 |
},
|
276 |
{
|
277 |
"id": 35079,
|
278 |
-
"content": "</
|
279 |
"single_word": false,
|
280 |
"lstrip": false,
|
281 |
"rstrip": false,
|
@@ -284,7 +284,7 @@
|
|
284 |
},
|
285 |
{
|
286 |
"id": 35080,
|
287 |
-
"content": "<
|
288 |
"single_word": false,
|
289 |
"lstrip": false,
|
290 |
"rstrip": false,
|
@@ -293,7 +293,7 @@
|
|
293 |
},
|
294 |
{
|
295 |
"id": 35081,
|
296 |
-
"content": "</
|
297 |
"single_word": false,
|
298 |
"lstrip": false,
|
299 |
"rstrip": false,
|
@@ -302,7 +302,7 @@
|
|
302 |
},
|
303 |
{
|
304 |
"id": 35082,
|
305 |
-
"content": "<
|
306 |
"single_word": false,
|
307 |
"lstrip": false,
|
308 |
"rstrip": false,
|
@@ -311,7 +311,7 @@
|
|
311 |
},
|
312 |
{
|
313 |
"id": 35083,
|
314 |
-
"content": "</
|
315 |
"single_word": false,
|
316 |
"lstrip": false,
|
317 |
"rstrip": false,
|
@@ -320,7 +320,7 @@
|
|
320 |
},
|
321 |
{
|
322 |
"id": 35084,
|
323 |
-
"content": "<
|
324 |
"single_word": false,
|
325 |
"lstrip": false,
|
326 |
"rstrip": false,
|
@@ -329,7 +329,7 @@
|
|
329 |
},
|
330 |
{
|
331 |
"id": 35085,
|
332 |
-
"content": "</
|
333 |
"single_word": false,
|
334 |
"lstrip": false,
|
335 |
"rstrip": false,
|
@@ -338,7 +338,7 @@
|
|
338 |
},
|
339 |
{
|
340 |
"id": 35086,
|
341 |
-
"content": "<
|
342 |
"single_word": false,
|
343 |
"lstrip": false,
|
344 |
"rstrip": false,
|
@@ -347,7 +347,7 @@
|
|
347 |
},
|
348 |
{
|
349 |
"id": 35087,
|
350 |
-
"content": "</
|
351 |
"single_word": false,
|
352 |
"lstrip": false,
|
353 |
"rstrip": false,
|
@@ -356,7 +356,7 @@
|
|
356 |
},
|
357 |
{
|
358 |
"id": 35088,
|
359 |
-
"content": "<
|
360 |
"single_word": false,
|
361 |
"lstrip": false,
|
362 |
"rstrip": false,
|
@@ -365,7 +365,7 @@
|
|
365 |
},
|
366 |
{
|
367 |
"id": 35089,
|
368 |
-
"content": "</
|
369 |
"single_word": false,
|
370 |
"lstrip": false,
|
371 |
"rstrip": false,
|
@@ -374,7 +374,7 @@
|
|
374 |
},
|
375 |
{
|
376 |
"id": 35090,
|
377 |
-
"content": "<
|
378 |
"single_word": false,
|
379 |
"lstrip": false,
|
380 |
"rstrip": false,
|
@@ -383,7 +383,7 @@
|
|
383 |
},
|
384 |
{
|
385 |
"id": 35091,
|
386 |
-
"content": "</
|
387 |
"single_word": false,
|
388 |
"lstrip": false,
|
389 |
"rstrip": false,
|
|
|
266 |
},
|
267 |
{
|
268 |
"id": 35078,
|
269 |
+
"content": "<s_1_seriya_nomer_1>",
|
270 |
"single_word": false,
|
271 |
"lstrip": false,
|
272 |
"rstrip": false,
|
|
|
275 |
},
|
276 |
{
|
277 |
"id": 35079,
|
278 |
+
"content": "</s_1_seriya_nomer_1>",
|
279 |
"single_word": false,
|
280 |
"lstrip": false,
|
281 |
"rstrip": false,
|
|
|
284 |
},
|
285 |
{
|
286 |
"id": 35080,
|
287 |
+
"content": "<s_1_seriya_nomer_2>",
|
288 |
"single_word": false,
|
289 |
"lstrip": false,
|
290 |
"rstrip": false,
|
|
|
293 |
},
|
294 |
{
|
295 |
"id": 35081,
|
296 |
+
"content": "</s_1_seriya_nomer_2>",
|
297 |
"single_word": false,
|
298 |
"lstrip": false,
|
299 |
"rstrip": false,
|
|
|
302 |
},
|
303 |
{
|
304 |
"id": 35082,
|
305 |
+
"content": "<s_1_pasport_vydan3>",
|
306 |
"single_word": false,
|
307 |
"lstrip": false,
|
308 |
"rstrip": false,
|
|
|
311 |
},
|
312 |
{
|
313 |
"id": 35083,
|
314 |
+
"content": "</s_1_pasport_vydan3>",
|
315 |
"single_word": false,
|
316 |
"lstrip": false,
|
317 |
"rstrip": false,
|
|
|
320 |
},
|
321 |
{
|
322 |
"id": 35084,
|
323 |
+
"content": "<s_1_mesto_rozhdeniya2>",
|
324 |
"single_word": false,
|
325 |
"lstrip": false,
|
326 |
"rstrip": false,
|
|
|
329 |
},
|
330 |
{
|
331 |
"id": 35085,
|
332 |
+
"content": "</s_1_mesto_rozhdeniya2>",
|
333 |
"single_word": false,
|
334 |
"lstrip": false,
|
335 |
"rstrip": false,
|
|
|
338 |
},
|
339 |
{
|
340 |
"id": 35086,
|
341 |
+
"content": "<s_1_mashinnyj_tekst_1>",
|
342 |
"single_word": false,
|
343 |
"lstrip": false,
|
344 |
"rstrip": false,
|
|
|
347 |
},
|
348 |
{
|
349 |
"id": 35087,
|
350 |
+
"content": "</s_1_mashinnyj_tekst_1>",
|
351 |
"single_word": false,
|
352 |
"lstrip": false,
|
353 |
"rstrip": false,
|
|
|
356 |
},
|
357 |
{
|
358 |
"id": 35088,
|
359 |
+
"content": "<s_1_mashinnyj_tekst_2>",
|
360 |
"single_word": false,
|
361 |
"lstrip": false,
|
362 |
"rstrip": false,
|
|
|
365 |
},
|
366 |
{
|
367 |
"id": 35089,
|
368 |
+
"content": "</s_1_mashinnyj_tekst_2>",
|
369 |
"single_word": false,
|
370 |
"lstrip": false,
|
371 |
"rstrip": false,
|
|
|
374 |
},
|
375 |
{
|
376 |
"id": 35090,
|
377 |
+
"content": "<s_1_mesto_rozhdeniya3>",
|
378 |
"single_word": false,
|
379 |
"lstrip": false,
|
380 |
"rstrip": false,
|
|
|
383 |
},
|
384 |
{
|
385 |
"id": 35091,
|
386 |
+
"content": "</s_1_mesto_rozhdeniya3>",
|
387 |
"single_word": false,
|
388 |
"lstrip": false,
|
389 |
"rstrip": false,
|