Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +971 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,971 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<s>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "</s>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<unk>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "<pad>",
|
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": {
|
53 |
+
"type": "Sequence",
|
54 |
+
"normalizers": [
|
55 |
+
{
|
56 |
+
"type": "Replace",
|
57 |
+
"pattern": {
|
58 |
+
"String": "``"
|
59 |
+
},
|
60 |
+
"content": "\""
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"type": "Replace",
|
64 |
+
"pattern": {
|
65 |
+
"String": "''"
|
66 |
+
},
|
67 |
+
"content": "\""
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"type": "Lowercase"
|
71 |
+
}
|
72 |
+
]
|
73 |
+
},
|
74 |
+
"pre_tokenizer": {
|
75 |
+
"type": "Metaspace",
|
76 |
+
"replacement": "▁",
|
77 |
+
"add_prefix_space": true
|
78 |
+
},
|
79 |
+
"post_processor": {
|
80 |
+
"type": "TemplateProcessing",
|
81 |
+
"single": [
|
82 |
+
{
|
83 |
+
"SpecialToken": {
|
84 |
+
"id": "<s>",
|
85 |
+
"type_id": 0
|
86 |
+
}
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"Sequence": {
|
90 |
+
"id": "A",
|
91 |
+
"type_id": 0
|
92 |
+
}
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"SpecialToken": {
|
96 |
+
"id": "</s>",
|
97 |
+
"type_id": 0
|
98 |
+
}
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"pair": [
|
102 |
+
{
|
103 |
+
"SpecialToken": {
|
104 |
+
"id": "<s>",
|
105 |
+
"type_id": 0
|
106 |
+
}
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"Sequence": {
|
110 |
+
"id": "A",
|
111 |
+
"type_id": 0
|
112 |
+
}
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"SpecialToken": {
|
116 |
+
"id": "</s>",
|
117 |
+
"type_id": 0
|
118 |
+
}
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"SpecialToken": {
|
122 |
+
"id": "<s>",
|
123 |
+
"type_id": 1
|
124 |
+
}
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"Sequence": {
|
128 |
+
"id": "B",
|
129 |
+
"type_id": 1
|
130 |
+
}
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"SpecialToken": {
|
134 |
+
"id": "</s>",
|
135 |
+
"type_id": 1
|
136 |
+
}
|
137 |
+
}
|
138 |
+
],
|
139 |
+
"special_tokens": {
|
140 |
+
"</s>": {
|
141 |
+
"id": "</s>",
|
142 |
+
"ids": [
|
143 |
+
1
|
144 |
+
],
|
145 |
+
"tokens": [
|
146 |
+
"</s>"
|
147 |
+
]
|
148 |
+
},
|
149 |
+
"<s>": {
|
150 |
+
"id": "<s>",
|
151 |
+
"ids": [
|
152 |
+
0
|
153 |
+
],
|
154 |
+
"tokens": [
|
155 |
+
"<s>"
|
156 |
+
]
|
157 |
+
}
|
158 |
+
}
|
159 |
+
},
|
160 |
+
"decoder": {
|
161 |
+
"type": "Metaspace",
|
162 |
+
"replacement": "▁",
|
163 |
+
"add_prefix_space": true
|
164 |
+
},
|
165 |
+
"model": {
|
166 |
+
"type": "Unigram",
|
167 |
+
"unk_id": 2,
|
168 |
+
"vocab": [
|
169 |
+
[
|
170 |
+
"<s>",
|
171 |
+
0.0
|
172 |
+
],
|
173 |
+
[
|
174 |
+
"</s>",
|
175 |
+
0.0
|
176 |
+
],
|
177 |
+
[
|
178 |
+
"<unk>",
|
179 |
+
0.0
|
180 |
+
],
|
181 |
+
[
|
182 |
+
"<pad>",
|
183 |
+
0.0
|
184 |
+
],
|
185 |
+
[
|
186 |
+
"<mask>",
|
187 |
+
0.0
|
188 |
+
],
|
189 |
+
[
|
190 |
+
"▁",
|
191 |
+
-2.933881842641904
|
192 |
+
],
|
193 |
+
[
|
194 |
+
".",
|
195 |
+
-3.5477780942834354
|
196 |
+
],
|
197 |
+
[
|
198 |
+
"t",
|
199 |
+
-3.589490346893994
|
200 |
+
],
|
201 |
+
[
|
202 |
+
"a",
|
203 |
+
-3.644247019210544
|
204 |
+
],
|
205 |
+
[
|
206 |
+
"m",
|
207 |
+
-3.6586101480214985
|
208 |
+
],
|
209 |
+
[
|
210 |
+
"o",
|
211 |
+
-3.70095367793402
|
212 |
+
],
|
213 |
+
[
|
214 |
+
"l",
|
215 |
+
-3.7651406443688806
|
216 |
+
],
|
217 |
+
[
|
218 |
+
"d",
|
219 |
+
-3.8417028391607904
|
220 |
+
],
|
221 |
+
[
|
222 |
+
"s",
|
223 |
+
-3.885144751638135
|
224 |
+
],
|
225 |
+
[
|
226 |
+
"r",
|
227 |
+
-3.901295045785892
|
228 |
+
],
|
229 |
+
[
|
230 |
+
"v",
|
231 |
+
-3.935602964994691
|
232 |
+
],
|
233 |
+
[
|
234 |
+
"e",
|
235 |
+
-3.9940703496517287
|
236 |
+
],
|
237 |
+
[
|
238 |
+
"á",
|
239 |
+
-4.033966857289286
|
240 |
+
],
|
241 |
+
[
|
242 |
+
"u",
|
243 |
+
-4.05884556484637
|
244 |
+
],
|
245 |
+
[
|
246 |
+
"i",
|
247 |
+
-4.1166233920812925
|
248 |
+
],
|
249 |
+
[
|
250 |
+
"p",
|
251 |
+
-4.176589139748492
|
252 |
+
],
|
253 |
+
[
|
254 |
+
"ní",
|
255 |
+
-4.279857833700591
|
256 |
+
],
|
257 |
+
[
|
258 |
+
"k",
|
259 |
+
-4.289690282403042
|
260 |
+
],
|
261 |
+
[
|
262 |
+
"í",
|
263 |
+
-4.293029126936448
|
264 |
+
],
|
265 |
+
[
|
266 |
+
"ch",
|
267 |
+
-4.324255581534921
|
268 |
+
],
|
269 |
+
[
|
270 |
+
"▁s",
|
271 |
+
-4.325405861628145
|
272 |
+
],
|
273 |
+
[
|
274 |
+
"n",
|
275 |
+
-4.37776141455995
|
276 |
+
],
|
277 |
+
[
|
278 |
+
"▁v",
|
279 |
+
-4.380004094093257
|
280 |
+
],
|
281 |
+
[
|
282 |
+
"st",
|
283 |
+
-4.453846829326743
|
284 |
+
],
|
285 |
+
[
|
286 |
+
"y",
|
287 |
+
-4.488741049922906
|
288 |
+
],
|
289 |
+
[
|
290 |
+
"b",
|
291 |
+
-4.501608535676114
|
292 |
+
],
|
293 |
+
[
|
294 |
+
"z",
|
295 |
+
-4.555001955831841
|
296 |
+
],
|
297 |
+
[
|
298 |
+
"ě",
|
299 |
+
-4.595063469625593
|
300 |
+
],
|
301 |
+
[
|
302 |
+
"▁a",
|
303 |
+
-4.6643161816163765
|
304 |
+
],
|
305 |
+
[
|
306 |
+
"▁po",
|
307 |
+
-4.716152885007917
|
308 |
+
],
|
309 |
+
[
|
310 |
+
"le",
|
311 |
+
-4.729191738166342
|
312 |
+
],
|
313 |
+
[
|
314 |
+
"▁je",
|
315 |
+
-4.771673455593422
|
316 |
+
],
|
317 |
+
[
|
318 |
+
"é",
|
319 |
+
-4.824781856505561
|
320 |
+
],
|
321 |
+
[
|
322 |
+
"▁z",
|
323 |
+
-4.8481232618122245
|
324 |
+
],
|
325 |
+
[
|
326 |
+
"▁na",
|
327 |
+
-4.9181854570660395
|
328 |
+
],
|
329 |
+
[
|
330 |
+
"ra",
|
331 |
+
-4.9291603874766015
|
332 |
+
],
|
333 |
+
[
|
334 |
+
"la",
|
335 |
+
-4.9390965232116475
|
336 |
+
],
|
337 |
+
[
|
338 |
+
"▁se",
|
339 |
+
-4.940769771372215
|
340 |
+
],
|
341 |
+
[
|
342 |
+
"ho",
|
343 |
+
-4.948526161364832
|
344 |
+
],
|
345 |
+
[
|
346 |
+
"ů",
|
347 |
+
-4.960219219866243
|
348 |
+
],
|
349 |
+
[
|
350 |
+
"č",
|
351 |
+
-4.97484752703166
|
352 |
+
],
|
353 |
+
[
|
354 |
+
"h",
|
355 |
+
-4.975810635483684
|
356 |
+
],
|
357 |
+
[
|
358 |
+
"ž",
|
359 |
+
-4.994197816023373
|
360 |
+
],
|
361 |
+
[
|
362 |
+
"ně",
|
363 |
+
-5.0492874780193056
|
364 |
+
],
|
365 |
+
[
|
366 |
+
"ce",
|
367 |
+
-5.055632153128059
|
368 |
+
],
|
369 |
+
[
|
370 |
+
"▁t",
|
371 |
+
-5.067221321042702
|
372 |
+
],
|
373 |
+
[
|
374 |
+
"c",
|
375 |
+
-5.103308475546731
|
376 |
+
],
|
377 |
+
[
|
378 |
+
"j",
|
379 |
+
-5.113139030749984
|
380 |
+
],
|
381 |
+
[
|
382 |
+
"▁k",
|
383 |
+
-5.121312549520173
|
384 |
+
],
|
385 |
+
[
|
386 |
+
"li",
|
387 |
+
-5.158555052585243
|
388 |
+
],
|
389 |
+
[
|
390 |
+
"to",
|
391 |
+
-5.187829843778575
|
392 |
+
],
|
393 |
+
[
|
394 |
+
"te",
|
395 |
+
-5.199580018751819
|
396 |
+
],
|
397 |
+
[
|
398 |
+
"ni",
|
399 |
+
-5.237632267398226
|
400 |
+
],
|
401 |
+
[
|
402 |
+
"va",
|
403 |
+
-5.271035361443101
|
404 |
+
],
|
405 |
+
[
|
406 |
+
"▁o",
|
407 |
+
-5.286563564192571
|
408 |
+
],
|
409 |
+
[
|
410 |
+
"ou",
|
411 |
+
-5.299940532930255
|
412 |
+
],
|
413 |
+
[
|
414 |
+
"▁do",
|
415 |
+
-5.315008911633093
|
416 |
+
],
|
417 |
+
[
|
418 |
+
"▁b",
|
419 |
+
-5.321459316608349
|
420 |
+
],
|
421 |
+
[
|
422 |
+
"lo",
|
423 |
+
-5.337670312261877
|
424 |
+
],
|
425 |
+
[
|
426 |
+
"na",
|
427 |
+
-5.3707587757007245
|
428 |
+
],
|
429 |
+
[
|
430 |
+
"▁pro",
|
431 |
+
-5.400835750750204
|
432 |
+
],
|
433 |
+
[
|
434 |
+
"ro",
|
435 |
+
-5.407363420434973
|
436 |
+
],
|
437 |
+
[
|
438 |
+
"š",
|
439 |
+
-5.410775069982266
|
440 |
+
],
|
441 |
+
[
|
442 |
+
"▁d",
|
443 |
+
-5.416578704818147
|
444 |
+
],
|
445 |
+
[
|
446 |
+
"ý",
|
447 |
+
-5.425608165733997
|
448 |
+
],
|
449 |
+
[
|
450 |
+
"en",
|
451 |
+
-5.431546361498073
|
452 |
+
],
|
453 |
+
[
|
454 |
+
"ře",
|
455 |
+
-5.446446776902486
|
456 |
+
],
|
457 |
+
[
|
458 |
+
"g",
|
459 |
+
-5.472971854258994
|
460 |
+
],
|
461 |
+
[
|
462 |
+
"▁ne",
|
463 |
+
-5.48942936029952
|
464 |
+
],
|
465 |
+
[
|
466 |
+
"▁za",
|
467 |
+
-5.5360003618990365
|
468 |
+
],
|
469 |
+
[
|
470 |
+
"em",
|
471 |
+
-5.540943553270047
|
472 |
+
],
|
473 |
+
[
|
474 |
+
"ko",
|
475 |
+
-5.551449196510767
|
476 |
+
],
|
477 |
+
[
|
478 |
+
"né",
|
479 |
+
-5.622361112385544
|
480 |
+
],
|
481 |
+
[
|
482 |
+
"▁h",
|
483 |
+
-5.6239437580030085
|
484 |
+
],
|
485 |
+
[
|
486 |
+
"de",
|
487 |
+
-5.643325386718073
|
488 |
+
],
|
489 |
+
[
|
490 |
+
"ti",
|
491 |
+
-5.6447253918913765
|
492 |
+
],
|
493 |
+
[
|
494 |
+
"▁byl",
|
495 |
+
-5.648337857155493
|
496 |
+
],
|
497 |
+
[
|
498 |
+
"ka",
|
499 |
+
-5.654853359802825
|
500 |
+
],
|
501 |
+
[
|
502 |
+
"ku",
|
503 |
+
-5.664006533642916
|
504 |
+
],
|
505 |
+
[
|
506 |
+
"▁ve",
|
507 |
+
-5.725900255027681
|
508 |
+
],
|
509 |
+
[
|
510 |
+
"ci",
|
511 |
+
-5.7649409188479614
|
512 |
+
],
|
513 |
+
[
|
514 |
+
"ná",
|
515 |
+
-5.769164693906317
|
516 |
+
],
|
517 |
+
[
|
518 |
+
"mi",
|
519 |
+
-5.774644808059395
|
520 |
+
],
|
521 |
+
[
|
522 |
+
"▁ob",
|
523 |
+
-5.778962817957801
|
524 |
+
],
|
525 |
+
[
|
526 |
+
"▁vy",
|
527 |
+
-5.789650303559062
|
528 |
+
],
|
529 |
+
[
|
530 |
+
"jí",
|
531 |
+
-5.794495124613842
|
532 |
+
],
|
533 |
+
[
|
534 |
+
"vě",
|
535 |
+
-5.798185586095333
|
536 |
+
],
|
537 |
+
[
|
538 |
+
"me",
|
539 |
+
-5.80913158514987
|
540 |
+
],
|
541 |
+
[
|
542 |
+
"ze",
|
543 |
+
-5.814166428372028
|
544 |
+
],
|
545 |
+
[
|
546 |
+
"▁p",
|
547 |
+
-5.824208440583925
|
548 |
+
],
|
549 |
+
[
|
550 |
+
"▁u",
|
551 |
+
-5.878757555875056
|
552 |
+
],
|
553 |
+
[
|
554 |
+
",",
|
555 |
+
-5.903152170013643
|
556 |
+
],
|
557 |
+
[
|
558 |
+
"no",
|
559 |
+
-5.9057725403152395
|
560 |
+
],
|
561 |
+
[
|
562 |
+
"ji",
|
563 |
+
-5.920428277572507
|
564 |
+
],
|
565 |
+
[
|
566 |
+
"▁to",
|
567 |
+
-5.926340496642947
|
568 |
+
],
|
569 |
+
[
|
570 |
+
"tu",
|
571 |
+
-5.927828549586592
|
572 |
+
],
|
573 |
+
[
|
574 |
+
"ky",
|
575 |
+
-5.9371858287916615
|
576 |
+
],
|
577 |
+
[
|
578 |
+
"or",
|
579 |
+
-5.946365129713133
|
580 |
+
],
|
581 |
+
[
|
582 |
+
"ný",
|
583 |
+
-5.99112481218983
|
584 |
+
],
|
585 |
+
[
|
586 |
+
"že",
|
587 |
+
-5.993760496634453
|
588 |
+
],
|
589 |
+
[
|
590 |
+
"ské",
|
591 |
+
-6.004036828021916
|
592 |
+
],
|
593 |
+
[
|
594 |
+
"ř",
|
595 |
+
-6.043049654958058
|
596 |
+
],
|
597 |
+
[
|
598 |
+
"in",
|
599 |
+
-6.044865678749619
|
600 |
+
],
|
601 |
+
[
|
602 |
+
"y.",
|
603 |
+
-6.064267907044521
|
604 |
+
],
|
605 |
+
[
|
606 |
+
"ší",
|
607 |
+
-6.066469419035859
|
608 |
+
],
|
609 |
+
[
|
610 |
+
"▁f",
|
611 |
+
-6.086007502509733
|
612 |
+
],
|
613 |
+
[
|
614 |
+
"vá",
|
615 |
+
-6.0929776823686215
|
616 |
+
],
|
617 |
+
[
|
618 |
+
"cí",
|
619 |
+
-6.096087103918272
|
620 |
+
],
|
621 |
+
[
|
622 |
+
"di",
|
623 |
+
-6.1258326693684
|
624 |
+
],
|
625 |
+
[
|
626 |
+
"ri",
|
627 |
+
-6.130335674191909
|
628 |
+
],
|
629 |
+
[
|
630 |
+
"je",
|
631 |
+
-6.137264395372371
|
632 |
+
],
|
633 |
+
[
|
634 |
+
"ne",
|
635 |
+
-6.1531957187534765
|
636 |
+
],
|
637 |
+
[
|
638 |
+
"▁vý",
|
639 |
+
-6.156522965057197
|
640 |
+
],
|
641 |
+
[
|
642 |
+
"▁ná",
|
643 |
+
-6.183729574743225
|
644 |
+
],
|
645 |
+
[
|
646 |
+
"ří",
|
647 |
+
-6.188204941940626
|
648 |
+
],
|
649 |
+
[
|
650 |
+
"▁pa",
|
651 |
+
-6.19758569914038
|
652 |
+
],
|
653 |
+
[
|
654 |
+
"ny",
|
655 |
+
-6.204870892400333
|
656 |
+
],
|
657 |
+
[
|
658 |
+
"ži",
|
659 |
+
-6.211094353405346
|
660 |
+
],
|
661 |
+
[
|
662 |
+
"oval",
|
663 |
+
-6.239595170380871
|
664 |
+
],
|
665 |
+
[
|
666 |
+
"f",
|
667 |
+
-6.286645633774842
|
668 |
+
],
|
669 |
+
[
|
670 |
+
"še",
|
671 |
+
-6.287121444594022
|
672 |
+
],
|
673 |
+
[
|
674 |
+
"▁ú",
|
675 |
+
-6.295293312777933
|
676 |
+
],
|
677 |
+
[
|
678 |
+
"by",
|
679 |
+
-6.301525122964281
|
680 |
+
],
|
681 |
+
[
|
682 |
+
"ru",
|
683 |
+
-6.30809270263456
|
684 |
+
],
|
685 |
+
[
|
686 |
+
"▁od",
|
687 |
+
-6.319961842625641
|
688 |
+
],
|
689 |
+
[
|
690 |
+
"▁zá",
|
691 |
+
-6.328547643992921
|
692 |
+
],
|
693 |
+
[
|
694 |
+
"vi",
|
695 |
+
-6.346802728367797
|
696 |
+
],
|
697 |
+
[
|
698 |
+
"▁ma",
|
699 |
+
-6.431912156242294
|
700 |
+
],
|
701 |
+
[
|
702 |
+
"lu",
|
703 |
+
-6.432754126816632
|
704 |
+
],
|
705 |
+
[
|
706 |
+
"uje",
|
707 |
+
-6.443190781270953
|
708 |
+
],
|
709 |
+
[
|
710 |
+
"ové",
|
711 |
+
-6.467014285714815
|
712 |
+
],
|
713 |
+
[
|
714 |
+
"nost",
|
715 |
+
-6.549975301817593
|
716 |
+
],
|
717 |
+
[
|
718 |
+
"▁pří",
|
719 |
+
-6.5569172549306725
|
720 |
+
],
|
721 |
+
[
|
722 |
+
"nu",
|
723 |
+
-6.570250699560692
|
724 |
+
],
|
725 |
+
[
|
726 |
+
"▁roz",
|
727 |
+
-6.589732746829957
|
728 |
+
],
|
729 |
+
[
|
730 |
+
"▁mo",
|
731 |
+
-6.5921275544955575
|
732 |
+
],
|
733 |
+
[
|
734 |
+
"▁při",
|
735 |
+
-6.592289291694437
|
736 |
+
],
|
737 |
+
[
|
738 |
+
"▁sta",
|
739 |
+
-6.604274711569781
|
740 |
+
],
|
741 |
+
[
|
742 |
+
"▁jako",
|
743 |
+
-6.640631120618143
|
744 |
+
],
|
745 |
+
[
|
746 |
+
"▁re",
|
747 |
+
-6.641361350548964
|
748 |
+
],
|
749 |
+
[
|
750 |
+
"▁pře",
|
751 |
+
-6.645933416903996
|
752 |
+
],
|
753 |
+
[
|
754 |
+
"ři",
|
755 |
+
-6.665728435048961
|
756 |
+
],
|
757 |
+
[
|
758 |
+
"▁před",
|
759 |
+
-6.688395456755879
|
760 |
+
],
|
761 |
+
[
|
762 |
+
"ován",
|
763 |
+
-6.6986357693587975
|
764 |
+
],
|
765 |
+
[
|
766 |
+
"ský",
|
767 |
+
-6.7345275093187515
|
768 |
+
],
|
769 |
+
[
|
770 |
+
"či",
|
771 |
+
-6.7556332887967985
|
772 |
+
],
|
773 |
+
[
|
774 |
+
"stav",
|
775 |
+
-6.7565629986059985
|
776 |
+
],
|
777 |
+
[
|
778 |
+
"▁také",
|
779 |
+
-6.784564208271911
|
780 |
+
],
|
781 |
+
[
|
782 |
+
"ické",
|
783 |
+
-6.822473413154058
|
784 |
+
],
|
785 |
+
[
|
786 |
+
"▁jsou",
|
787 |
+
-6.839600800409185
|
788 |
+
],
|
789 |
+
[
|
790 |
+
"▁kon",
|
791 |
+
-6.856932521302764
|
792 |
+
],
|
793 |
+
[
|
794 |
+
"\"",
|
795 |
+
-6.940649196032627
|
796 |
+
],
|
797 |
+
[
|
798 |
+
"děl",
|
799 |
+
-7.012240797906627
|
800 |
+
],
|
801 |
+
[
|
802 |
+
"▁tak",
|
803 |
+
-7.056427922232195
|
804 |
+
],
|
805 |
+
[
|
806 |
+
"▁ja",
|
807 |
+
-7.059445413822217
|
808 |
+
],
|
809 |
+
[
|
810 |
+
"cký",
|
811 |
+
-7.083248888291322
|
812 |
+
],
|
813 |
+
[
|
814 |
+
"x",
|
815 |
+
-7.094945147217752
|
816 |
+
],
|
817 |
+
[
|
818 |
+
"ň",
|
819 |
+
-7.16444676938674
|
820 |
+
],
|
821 |
+
[
|
822 |
+
"▁však",
|
823 |
+
-7.188759209502638
|
824 |
+
],
|
825 |
+
[
|
826 |
+
"ště",
|
827 |
+
-7.197130013703209
|
828 |
+
],
|
829 |
+
[
|
830 |
+
"▁měst",
|
831 |
+
-7.2631846765783745
|
832 |
+
],
|
833 |
+
[
|
834 |
+
"▁druh",
|
835 |
+
-7.282570677527317
|
836 |
+
],
|
837 |
+
[
|
838 |
+
"▁měl",
|
839 |
+
-7.384552941270997
|
840 |
+
],
|
841 |
+
[
|
842 |
+
"?",
|
843 |
+
-7.407692759728381
|
844 |
+
],
|
845 |
+
[
|
846 |
+
"chází",
|
847 |
+
-7.435960685282815
|
848 |
+
],
|
849 |
+
[
|
850 |
+
"▁mezi",
|
851 |
+
-7.507108909210451
|
852 |
+
],
|
853 |
+
[
|
854 |
+
"w",
|
855 |
+
-7.535083601752331
|
856 |
+
],
|
857 |
+
[
|
858 |
+
"▁několik",
|
859 |
+
-7.590293335462103
|
860 |
+
],
|
861 |
+
[
|
862 |
+
"▁musí",
|
863 |
+
-7.677520603750372
|
864 |
+
],
|
865 |
+
[
|
866 |
+
"▁později",
|
867 |
+
-7.718353421312045
|
868 |
+
],
|
869 |
+
[
|
870 |
+
"▁evropsk",
|
871 |
+
-7.830696406547949
|
872 |
+
],
|
873 |
+
[
|
874 |
+
"▁společn",
|
875 |
+
-7.874088576602077
|
876 |
+
],
|
877 |
+
[
|
878 |
+
"ť",
|
879 |
+
-7.901054161965922
|
880 |
+
],
|
881 |
+
[
|
882 |
+
"▁současn",
|
883 |
+
-7.9524684253043665
|
884 |
+
],
|
885 |
+
[
|
886 |
+
"ď",
|
887 |
+
-8.011743748876743
|
888 |
+
],
|
889 |
+
[
|
890 |
+
"ó",
|
891 |
+
-8.058627228696277
|
892 |
+
],
|
893 |
+
[
|
894 |
+
"!",
|
895 |
+
-8.390840756999921
|
896 |
+
],
|
897 |
+
[
|
898 |
+
"▁působil",
|
899 |
+
-8.398303443996245
|
900 |
+
],
|
901 |
+
[
|
902 |
+
"▁univerzit",
|
903 |
+
-8.428723893618406
|
904 |
+
],
|
905 |
+
[
|
906 |
+
"ú",
|
907 |
+
-8.69197148730532
|
908 |
+
],
|
909 |
+
[
|
910 |
+
"“",
|
911 |
+
-8.798163432450156
|
912 |
+
],
|
913 |
+
[
|
914 |
+
"-",
|
915 |
+
-9.81112772875104
|
916 |
+
],
|
917 |
+
[
|
918 |
+
"–",
|
919 |
+
-10.093664746434053
|
920 |
+
],
|
921 |
+
[
|
922 |
+
";",
|
923 |
+
-10.766412245976962
|
924 |
+
],
|
925 |
+
[
|
926 |
+
"ö",
|
927 |
+
-10.940654670219764
|
928 |
+
],
|
929 |
+
[
|
930 |
+
"ü",
|
931 |
+
-11.276765781343222
|
932 |
+
],
|
933 |
+
[
|
934 |
+
"/",
|
935 |
+
-12.36962292424032
|
936 |
+
],
|
937 |
+
[
|
938 |
+
"è",
|
939 |
+
-12.369622924240325
|
940 |
+
],
|
941 |
+
[
|
942 |
+
"ä",
|
943 |
+
-12.86962292424032
|
944 |
+
],
|
945 |
+
[
|
946 |
+
":",
|
947 |
+
-12.869622924240325
|
948 |
+
],
|
949 |
+
[
|
950 |
+
"q",
|
951 |
+
-13.869522924240323
|
952 |
+
],
|
953 |
+
[
|
954 |
+
"„",
|
955 |
+
-13.869622924240325
|
956 |
+
],
|
957 |
+
[
|
958 |
+
"—",
|
959 |
+
-13.869622924240325
|
960 |
+
],
|
961 |
+
[
|
962 |
+
"…",
|
963 |
+
-13.869622924240325
|
964 |
+
],
|
965 |
+
[
|
966 |
+
"ï",
|
967 |
+
-13.869622924240325
|
968 |
+
]
|
969 |
+
]
|
970 |
+
}
|
971 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|