Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +340 -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 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"L",
|
160 |
+
-2.7509312510529185
|
161 |
+
],
|
162 |
+
[
|
163 |
+
"R",
|
164 |
+
-2.755084699217022
|
165 |
+
],
|
166 |
+
[
|
167 |
+
"V",
|
168 |
+
-2.8114993435449485
|
169 |
+
],
|
170 |
+
[
|
171 |
+
"T",
|
172 |
+
-2.818179108697013
|
173 |
+
],
|
174 |
+
[
|
175 |
+
"D",
|
176 |
+
-2.8358745908237744
|
177 |
+
],
|
178 |
+
[
|
179 |
+
"I",
|
180 |
+
-2.8386883982403575
|
181 |
+
],
|
182 |
+
[
|
183 |
+
"S",
|
184 |
+
-2.8508125229928503
|
185 |
+
],
|
186 |
+
[
|
187 |
+
"G",
|
188 |
+
-2.8876033679551227
|
189 |
+
],
|
190 |
+
[
|
191 |
+
"E",
|
192 |
+
-2.9024328890049524
|
193 |
+
],
|
194 |
+
[
|
195 |
+
"P",
|
196 |
+
-2.911018940638389
|
197 |
+
],
|
198 |
+
[
|
199 |
+
"K",
|
200 |
+
-2.9183231107580596
|
201 |
+
],
|
202 |
+
[
|
203 |
+
"A",
|
204 |
+
-2.919747614014888
|
205 |
+
],
|
206 |
+
[
|
207 |
+
"N",
|
208 |
+
-3.123051382634724
|
209 |
+
],
|
210 |
+
[
|
211 |
+
"F",
|
212 |
+
-3.17920066040503
|
213 |
+
],
|
214 |
+
[
|
215 |
+
"Q",
|
216 |
+
-3.190869184456883
|
217 |
+
],
|
218 |
+
[
|
219 |
+
"Y",
|
220 |
+
-3.4628954984309086
|
221 |
+
],
|
222 |
+
[
|
223 |
+
"H",
|
224 |
+
-3.741564333998106
|
225 |
+
],
|
226 |
+
[
|
227 |
+
"M",
|
228 |
+
-3.771740452244479
|
229 |
+
],
|
230 |
+
[
|
231 |
+
"C",
|
232 |
+
-4.177244477126914
|
233 |
+
],
|
234 |
+
[
|
235 |
+
"W",
|
236 |
+
-4.26244359647038
|
237 |
+
],
|
238 |
+
[
|
239 |
+
"AA",
|
240 |
+
-5.151553502459924
|
241 |
+
],
|
242 |
+
[
|
243 |
+
"LL",
|
244 |
+
-5.297524048938797
|
245 |
+
],
|
246 |
+
[
|
247 |
+
"LA",
|
248 |
+
-5.433632759818389
|
249 |
+
],
|
250 |
+
[
|
251 |
+
"AL",
|
252 |
+
-5.5585947635634465
|
253 |
+
],
|
254 |
+
[
|
255 |
+
"SS",
|
256 |
+
-5.653368570054353
|
257 |
+
],
|
258 |
+
[
|
259 |
+
"LS",
|
260 |
+
-5.6542024366077595
|
261 |
+
],
|
262 |
+
[
|
263 |
+
"SL",
|
264 |
+
-5.774350740282891
|
265 |
+
],
|
266 |
+
[
|
267 |
+
"AG",
|
268 |
+
-5.927206325143018
|
269 |
+
],
|
270 |
+
[
|
271 |
+
"VL",
|
272 |
+
-5.971670833218097
|
273 |
+
],
|
274 |
+
[
|
275 |
+
"GG",
|
276 |
+
-5.998372467775059
|
277 |
+
],
|
278 |
+
[
|
279 |
+
"VA",
|
280 |
+
-6.014387210129083
|
281 |
+
],
|
282 |
+
[
|
283 |
+
"SA",
|
284 |
+
-6.0238415835311105
|
285 |
+
],
|
286 |
+
[
|
287 |
+
"LV",
|
288 |
+
-6.027713726026638
|
289 |
+
],
|
290 |
+
[
|
291 |
+
"EL",
|
292 |
+
-6.053145724740345
|
293 |
+
],
|
294 |
+
[
|
295 |
+
"AV",
|
296 |
+
-6.058233627458359
|
297 |
+
],
|
298 |
+
[
|
299 |
+
"GA",
|
300 |
+
-6.083252372183383
|
301 |
+
],
|
302 |
+
[
|
303 |
+
"LG",
|
304 |
+
-6.1040977735585
|
305 |
+
],
|
306 |
+
[
|
307 |
+
"AS",
|
308 |
+
-6.118553954419422
|
309 |
+
],
|
310 |
+
[
|
311 |
+
"SG",
|
312 |
+
-6.132691839839374
|
313 |
+
],
|
314 |
+
[
|
315 |
+
"EA",
|
316 |
+
-6.152907367995331
|
317 |
+
],
|
318 |
+
[
|
319 |
+
"X",
|
320 |
+
-7.727541617091807
|
321 |
+
],
|
322 |
+
[
|
323 |
+
"B",
|
324 |
+
-14.572756361550985
|
325 |
+
],
|
326 |
+
[
|
327 |
+
"Z",
|
328 |
+
-15.799721233660796
|
329 |
+
],
|
330 |
+
[
|
331 |
+
"U",
|
332 |
+
-16.47917235225718
|
333 |
+
],
|
334 |
+
[
|
335 |
+
"O",
|
336 |
+
-19.974280430470184
|
337 |
+
]
|
338 |
+
]
|
339 |
+
}
|
340 |
+
}
|
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 |
+
}
|