Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +540 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<cls>",
|
3 |
+
"cls_token": "<cls>",
|
4 |
+
"eos_token": "<sep>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "<sep>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<pad>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<cls>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<sep>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "<unk>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "<mask>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": null,
|
53 |
+
"pre_tokenizer": null,
|
54 |
+
"post_processor": {
|
55 |
+
"type": "TemplateProcessing",
|
56 |
+
"single": [
|
57 |
+
{
|
58 |
+
"SpecialToken": {
|
59 |
+
"id": "<cls>",
|
60 |
+
"type_id": 0
|
61 |
+
}
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"Sequence": {
|
65 |
+
"id": "A",
|
66 |
+
"type_id": 0
|
67 |
+
}
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"SpecialToken": {
|
71 |
+
"id": "<sep>",
|
72 |
+
"type_id": 0
|
73 |
+
}
|
74 |
+
}
|
75 |
+
],
|
76 |
+
"pair": [
|
77 |
+
{
|
78 |
+
"SpecialToken": {
|
79 |
+
"id": "<cls>",
|
80 |
+
"type_id": 0
|
81 |
+
}
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"Sequence": {
|
85 |
+
"id": "A",
|
86 |
+
"type_id": 0
|
87 |
+
}
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"SpecialToken": {
|
91 |
+
"id": "<sep>",
|
92 |
+
"type_id": 0
|
93 |
+
}
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"Sequence": {
|
97 |
+
"id": "B",
|
98 |
+
"type_id": 1
|
99 |
+
}
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"SpecialToken": {
|
103 |
+
"id": "<sep>",
|
104 |
+
"type_id": 1
|
105 |
+
}
|
106 |
+
}
|
107 |
+
],
|
108 |
+
"special_tokens": {
|
109 |
+
"<cls>": {
|
110 |
+
"id": "<cls>",
|
111 |
+
"ids": [
|
112 |
+
1
|
113 |
+
],
|
114 |
+
"tokens": [
|
115 |
+
"<cls>"
|
116 |
+
]
|
117 |
+
},
|
118 |
+
"<sep>": {
|
119 |
+
"id": "<sep>",
|
120 |
+
"ids": [
|
121 |
+
2
|
122 |
+
],
|
123 |
+
"tokens": [
|
124 |
+
"<sep>"
|
125 |
+
]
|
126 |
+
}
|
127 |
+
}
|
128 |
+
},
|
129 |
+
"decoder": {
|
130 |
+
"type": "Metaspace",
|
131 |
+
"replacement": "▁",
|
132 |
+
"add_prefix_space": true
|
133 |
+
},
|
134 |
+
"model": {
|
135 |
+
"type": "Unigram",
|
136 |
+
"unk_id": 3,
|
137 |
+
"vocab": [
|
138 |
+
[
|
139 |
+
"<pad>",
|
140 |
+
0.0
|
141 |
+
],
|
142 |
+
[
|
143 |
+
"<cls>",
|
144 |
+
0.0
|
145 |
+
],
|
146 |
+
[
|
147 |
+
"<sep>",
|
148 |
+
0.0
|
149 |
+
],
|
150 |
+
[
|
151 |
+
"<unk>",
|
152 |
+
0.0
|
153 |
+
],
|
154 |
+
[
|
155 |
+
"<mask>",
|
156 |
+
0.0
|
157 |
+
],
|
158 |
+
[
|
159 |
+
"K",
|
160 |
+
-2.8926598139924984
|
161 |
+
],
|
162 |
+
[
|
163 |
+
"P",
|
164 |
+
-2.937301100450547
|
165 |
+
],
|
166 |
+
[
|
167 |
+
"R",
|
168 |
+
-2.981133587027994
|
169 |
+
],
|
170 |
+
[
|
171 |
+
"N",
|
172 |
+
-2.984398973523902
|
173 |
+
],
|
174 |
+
[
|
175 |
+
"F",
|
176 |
+
-3.0405482512940942
|
177 |
+
],
|
178 |
+
[
|
179 |
+
"Q",
|
180 |
+
-3.0522167753465475
|
181 |
+
],
|
182 |
+
[
|
183 |
+
"T",
|
184 |
+
-3.057893521866589
|
185 |
+
],
|
186 |
+
[
|
187 |
+
"D",
|
188 |
+
-3.221572989674069
|
189 |
+
],
|
190 |
+
[
|
191 |
+
"V",
|
192 |
+
-3.242957729449966
|
193 |
+
],
|
194 |
+
[
|
195 |
+
"I",
|
196 |
+
-3.2639228157131353
|
197 |
+
],
|
198 |
+
[
|
199 |
+
"G",
|
200 |
+
-3.292222729720054
|
201 |
+
],
|
202 |
+
[
|
203 |
+
"Y",
|
204 |
+
-3.3242430893206976
|
205 |
+
],
|
206 |
+
[
|
207 |
+
"E",
|
208 |
+
-3.329998422834164
|
209 |
+
],
|
210 |
+
[
|
211 |
+
"A",
|
212 |
+
-3.3315100842234955
|
213 |
+
],
|
214 |
+
[
|
215 |
+
"L",
|
216 |
+
-3.354133164459414
|
217 |
+
],
|
218 |
+
[
|
219 |
+
"S",
|
220 |
+
-3.374619245946816
|
221 |
+
],
|
222 |
+
[
|
223 |
+
"H",
|
224 |
+
-3.6029119248880974
|
225 |
+
],
|
226 |
+
[
|
227 |
+
"M",
|
228 |
+
-3.6330880431340073
|
229 |
+
],
|
230 |
+
[
|
231 |
+
"C",
|
232 |
+
-4.03859206801765
|
233 |
+
],
|
234 |
+
[
|
235 |
+
"W",
|
236 |
+
-4.123791187360837
|
237 |
+
],
|
238 |
+
[
|
239 |
+
"AA",
|
240 |
+
-4.973167425197216
|
241 |
+
],
|
242 |
+
[
|
243 |
+
"LL",
|
244 |
+
-5.036049835340242
|
245 |
+
],
|
246 |
+
[
|
247 |
+
"LA",
|
248 |
+
-5.194188976627833
|
249 |
+
],
|
250 |
+
[
|
251 |
+
"LS",
|
252 |
+
-5.284020121682021
|
253 |
+
],
|
254 |
+
[
|
255 |
+
"AL",
|
256 |
+
-5.320469682162143
|
257 |
+
],
|
258 |
+
[
|
259 |
+
"SS",
|
260 |
+
-5.32453022570105
|
261 |
+
],
|
262 |
+
[
|
263 |
+
"SL",
|
264 |
+
-5.499862731096803
|
265 |
+
],
|
266 |
+
[
|
267 |
+
"LV",
|
268 |
+
-5.564795933199976
|
269 |
+
],
|
270 |
+
[
|
271 |
+
"AG",
|
272 |
+
-5.570161883025232
|
273 |
+
],
|
274 |
+
[
|
275 |
+
"GG",
|
276 |
+
-5.586688874755673
|
277 |
+
],
|
278 |
+
[
|
279 |
+
"AV",
|
280 |
+
-5.633866882153034
|
281 |
+
],
|
282 |
+
[
|
283 |
+
"LG",
|
284 |
+
-5.6617838822297415
|
285 |
+
],
|
286 |
+
[
|
287 |
+
"EL",
|
288 |
+
-5.710679099236735
|
289 |
+
],
|
290 |
+
[
|
291 |
+
"AS",
|
292 |
+
-5.716264001404388
|
293 |
+
],
|
294 |
+
[
|
295 |
+
"VL",
|
296 |
+
-5.7256437689651545
|
297 |
+
],
|
298 |
+
[
|
299 |
+
"SG",
|
300 |
+
-5.727475385041664
|
301 |
+
],
|
302 |
+
[
|
303 |
+
"LR",
|
304 |
+
-5.728549131116866
|
305 |
+
],
|
306 |
+
[
|
307 |
+
"LE",
|
308 |
+
-5.743482374609412
|
309 |
+
],
|
310 |
+
[
|
311 |
+
"GL",
|
312 |
+
-5.743495521291919
|
313 |
+
],
|
314 |
+
[
|
315 |
+
"SA",
|
316 |
+
-5.761398906433778
|
317 |
+
],
|
318 |
+
[
|
319 |
+
"GA",
|
320 |
+
-5.779501575037608
|
321 |
+
],
|
322 |
+
[
|
323 |
+
"EE",
|
324 |
+
-5.783251373522621
|
325 |
+
],
|
326 |
+
[
|
327 |
+
"RL",
|
328 |
+
-5.787802487132645
|
329 |
+
],
|
330 |
+
[
|
331 |
+
"VA",
|
332 |
+
-5.822397606320607
|
333 |
+
],
|
334 |
+
[
|
335 |
+
"TL",
|
336 |
+
-5.826633127578567
|
337 |
+
],
|
338 |
+
[
|
339 |
+
"GS",
|
340 |
+
-5.836663706756646
|
341 |
+
],
|
342 |
+
[
|
343 |
+
"EA",
|
344 |
+
-5.854012392063035
|
345 |
+
],
|
346 |
+
[
|
347 |
+
"TA",
|
348 |
+
-5.87623583133286
|
349 |
+
],
|
350 |
+
[
|
351 |
+
"LD",
|
352 |
+
-5.884057317313408
|
353 |
+
],
|
354 |
+
[
|
355 |
+
"VV",
|
356 |
+
-5.886122471861352
|
357 |
+
],
|
358 |
+
[
|
359 |
+
"LT",
|
360 |
+
-5.890501009220628
|
361 |
+
],
|
362 |
+
[
|
363 |
+
"IL",
|
364 |
+
-5.893641541215938
|
365 |
+
],
|
366 |
+
[
|
367 |
+
"DL",
|
368 |
+
-5.908589432452223
|
369 |
+
],
|
370 |
+
[
|
371 |
+
"SV",
|
372 |
+
-5.928508582466128
|
373 |
+
],
|
374 |
+
[
|
375 |
+
"LP",
|
376 |
+
-5.930607331306064
|
377 |
+
],
|
378 |
+
[
|
379 |
+
"GV",
|
380 |
+
-5.931353514901755
|
381 |
+
],
|
382 |
+
[
|
383 |
+
"IS",
|
384 |
+
-5.934577159636316
|
385 |
+
],
|
386 |
+
[
|
387 |
+
"RR",
|
388 |
+
-5.937181139038799
|
389 |
+
],
|
390 |
+
[
|
391 |
+
"PA",
|
392 |
+
-5.95165892093522
|
393 |
+
],
|
394 |
+
[
|
395 |
+
"LI",
|
396 |
+
-5.956444805023796
|
397 |
+
],
|
398 |
+
[
|
399 |
+
"DG",
|
400 |
+
-5.959872500616557
|
401 |
+
],
|
402 |
+
[
|
403 |
+
"LK",
|
404 |
+
-5.977419747714027
|
405 |
+
],
|
406 |
+
[
|
407 |
+
"AE",
|
408 |
+
-5.988346330589572
|
409 |
+
],
|
410 |
+
[
|
411 |
+
"VS",
|
412 |
+
-5.992644676581763
|
413 |
+
],
|
414 |
+
[
|
415 |
+
"TV",
|
416 |
+
-5.992771047038934
|
417 |
+
],
|
418 |
+
[
|
419 |
+
"TS",
|
420 |
+
-5.992862744926201
|
421 |
+
],
|
422 |
+
[
|
423 |
+
"DA",
|
424 |
+
-6.005980312620514
|
425 |
+
],
|
426 |
+
[
|
427 |
+
"TG",
|
428 |
+
-6.020054424800335
|
429 |
+
],
|
430 |
+
[
|
431 |
+
"IA",
|
432 |
+
-6.029275865888938
|
433 |
+
],
|
434 |
+
[
|
435 |
+
"PS",
|
436 |
+
-6.0558861763675385
|
437 |
+
],
|
438 |
+
[
|
439 |
+
"RA",
|
440 |
+
-6.091301969244897
|
441 |
+
],
|
442 |
+
[
|
443 |
+
"EK",
|
444 |
+
-6.143807832748726
|
445 |
+
],
|
446 |
+
[
|
447 |
+
"EV",
|
448 |
+
-6.144172113809702
|
449 |
+
],
|
450 |
+
[
|
451 |
+
"ST",
|
452 |
+
-6.1659183042917824
|
453 |
+
],
|
454 |
+
[
|
455 |
+
"DE",
|
456 |
+
-6.175007806118581
|
457 |
+
],
|
458 |
+
[
|
459 |
+
"SI",
|
460 |
+
-6.196141783532548
|
461 |
+
],
|
462 |
+
[
|
463 |
+
"IV",
|
464 |
+
-6.203941668151083
|
465 |
+
],
|
466 |
+
[
|
467 |
+
"DV",
|
468 |
+
-6.2062585412907065
|
469 |
+
],
|
470 |
+
[
|
471 |
+
"AD",
|
472 |
+
-6.214482574668974
|
473 |
+
],
|
474 |
+
[
|
475 |
+
"RS",
|
476 |
+
-6.219463683778585
|
477 |
+
],
|
478 |
+
[
|
479 |
+
"EI",
|
480 |
+
-6.2248807356059555
|
481 |
+
],
|
482 |
+
[
|
483 |
+
"GE",
|
484 |
+
-6.253174496738863
|
485 |
+
],
|
486 |
+
[
|
487 |
+
"IE",
|
488 |
+
-6.264016428440042
|
489 |
+
],
|
490 |
+
[
|
491 |
+
"ES",
|
492 |
+
-6.272022775598392
|
493 |
+
],
|
494 |
+
[
|
495 |
+
"SE",
|
496 |
+
-6.288530115689479
|
497 |
+
],
|
498 |
+
[
|
499 |
+
"IG",
|
500 |
+
-6.300749800545876
|
501 |
+
],
|
502 |
+
[
|
503 |
+
"SD",
|
504 |
+
-6.305378344633647
|
505 |
+
],
|
506 |
+
[
|
507 |
+
"VG",
|
508 |
+
-6.307254140261982
|
509 |
+
],
|
510 |
+
[
|
511 |
+
"VE",
|
512 |
+
-6.322491387400987
|
513 |
+
],
|
514 |
+
[
|
515 |
+
"GI",
|
516 |
+
-6.346224238884332
|
517 |
+
],
|
518 |
+
[
|
519 |
+
"X",
|
520 |
+
-7.588889207971681
|
521 |
+
],
|
522 |
+
[
|
523 |
+
"B",
|
524 |
+
-14.434103952435104
|
525 |
+
],
|
526 |
+
[
|
527 |
+
"Z",
|
528 |
+
-15.661068824545652
|
529 |
+
],
|
530 |
+
[
|
531 |
+
"U",
|
532 |
+
-16.34051994314413
|
533 |
+
],
|
534 |
+
[
|
535 |
+
"O",
|
536 |
+
-19.83562802135349
|
537 |
+
]
|
538 |
+
]
|
539 |
+
}
|
540 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|