Upload tokenizer
Browse files- added_tokens.json +49 -1
- tokenizer.json +432 -0
- tokenizer_config.json +384 -0
added_tokens.json
CHANGED
@@ -1,3 +1,51 @@
|
|
1 |
{
|
2 |
-
"1 ": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"1 ": 1,
|
3 |
+
"10 ": 10,
|
4 |
+
"11 ": 11,
|
5 |
+
"12 ": 12,
|
6 |
+
"13 ": 13,
|
7 |
+
"14 ": 14,
|
8 |
+
"15 ": 15,
|
9 |
+
"16 ": 16,
|
10 |
+
"17 ": 17,
|
11 |
+
"18 ": 18,
|
12 |
+
"19 ": 19,
|
13 |
+
"2 ": 2,
|
14 |
+
"20 ": 20,
|
15 |
+
"21 ": 21,
|
16 |
+
"22 ": 22,
|
17 |
+
"23 ": 23,
|
18 |
+
"24 ": 24,
|
19 |
+
"25 ": 25,
|
20 |
+
"26 ": 26,
|
21 |
+
"27 ": 27,
|
22 |
+
"28 ": 28,
|
23 |
+
"29 ": 29,
|
24 |
+
"3 ": 3,
|
25 |
+
"30 ": 30,
|
26 |
+
"31 ": 31,
|
27 |
+
"32 ": 32,
|
28 |
+
"33 ": 33,
|
29 |
+
"34 ": 34,
|
30 |
+
"35 ": 35,
|
31 |
+
"36 ": 36,
|
32 |
+
"37 ": 37,
|
33 |
+
"38 ": 38,
|
34 |
+
"39 ": 39,
|
35 |
+
"4 ": 4,
|
36 |
+
"40 ": 40,
|
37 |
+
"41 ": 41,
|
38 |
+
"42 ": 42,
|
39 |
+
"43 ": 43,
|
40 |
+
"44 ": 44,
|
41 |
+
"45 ": 45,
|
42 |
+
"46 ": 46,
|
43 |
+
"47 ": 47,
|
44 |
+
"48 ": 48,
|
45 |
+
"49 ": 49,
|
46 |
+
"5 ": 5,
|
47 |
+
"6 ": 6,
|
48 |
+
"7 ": 7,
|
49 |
+
"8 ": 8,
|
50 |
+
"9 ": 9
|
51 |
}
|
tokenizer.json
CHANGED
@@ -20,6 +20,438 @@
|
|
20 |
"rstrip": false,
|
21 |
"normalized": false,
|
22 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
"normalizer": null,
|
|
|
20 |
"rstrip": false,
|
21 |
"normalized": false,
|
22 |
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "2 ",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"special": false
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "3 ",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"special": false
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "4 ",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "5 ",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
+
"content": "6 ",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 7,
|
71 |
+
"content": "7 ",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"normalized": true,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 8,
|
80 |
+
"content": "8 ",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
+
"normalized": true,
|
85 |
+
"special": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 9,
|
89 |
+
"content": "9 ",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"normalized": true,
|
94 |
+
"special": false
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 10,
|
98 |
+
"content": "10 ",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"special": false
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 11,
|
107 |
+
"content": "11 ",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"special": false
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"id": 12,
|
116 |
+
"content": "12 ",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 13,
|
125 |
+
"content": "13 ",
|
126 |
+
"single_word": false,
|
127 |
+
"lstrip": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 14,
|
134 |
+
"content": "14 ",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"normalized": true,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"id": 15,
|
143 |
+
"content": "15 ",
|
144 |
+
"single_word": false,
|
145 |
+
"lstrip": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"normalized": true,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"id": 16,
|
152 |
+
"content": "16 ",
|
153 |
+
"single_word": false,
|
154 |
+
"lstrip": false,
|
155 |
+
"rstrip": false,
|
156 |
+
"normalized": true,
|
157 |
+
"special": false
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"id": 17,
|
161 |
+
"content": "17 ",
|
162 |
+
"single_word": false,
|
163 |
+
"lstrip": false,
|
164 |
+
"rstrip": false,
|
165 |
+
"normalized": true,
|
166 |
+
"special": false
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"id": 18,
|
170 |
+
"content": "18 ",
|
171 |
+
"single_word": false,
|
172 |
+
"lstrip": false,
|
173 |
+
"rstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"special": false
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"id": 19,
|
179 |
+
"content": "19 ",
|
180 |
+
"single_word": false,
|
181 |
+
"lstrip": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"special": false
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"id": 20,
|
188 |
+
"content": "20 ",
|
189 |
+
"single_word": false,
|
190 |
+
"lstrip": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"normalized": true,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"id": 21,
|
197 |
+
"content": "21 ",
|
198 |
+
"single_word": false,
|
199 |
+
"lstrip": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"id": 22,
|
206 |
+
"content": "22 ",
|
207 |
+
"single_word": false,
|
208 |
+
"lstrip": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"normalized": true,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"id": 23,
|
215 |
+
"content": "23 ",
|
216 |
+
"single_word": false,
|
217 |
+
"lstrip": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"normalized": true,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"id": 24,
|
224 |
+
"content": "24 ",
|
225 |
+
"single_word": false,
|
226 |
+
"lstrip": false,
|
227 |
+
"rstrip": false,
|
228 |
+
"normalized": true,
|
229 |
+
"special": false
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"id": 25,
|
233 |
+
"content": "25 ",
|
234 |
+
"single_word": false,
|
235 |
+
"lstrip": false,
|
236 |
+
"rstrip": false,
|
237 |
+
"normalized": true,
|
238 |
+
"special": false
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"id": 26,
|
242 |
+
"content": "26 ",
|
243 |
+
"single_word": false,
|
244 |
+
"lstrip": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"special": false
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"id": 27,
|
251 |
+
"content": "27 ",
|
252 |
+
"single_word": false,
|
253 |
+
"lstrip": false,
|
254 |
+
"rstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"special": false
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"id": 28,
|
260 |
+
"content": "28 ",
|
261 |
+
"single_word": false,
|
262 |
+
"lstrip": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"normalized": true,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"id": 29,
|
269 |
+
"content": "29 ",
|
270 |
+
"single_word": false,
|
271 |
+
"lstrip": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"normalized": true,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"id": 30,
|
278 |
+
"content": "30 ",
|
279 |
+
"single_word": false,
|
280 |
+
"lstrip": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"normalized": true,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"id": 31,
|
287 |
+
"content": "31 ",
|
288 |
+
"single_word": false,
|
289 |
+
"lstrip": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"normalized": true,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"id": 32,
|
296 |
+
"content": "32 ",
|
297 |
+
"single_word": false,
|
298 |
+
"lstrip": false,
|
299 |
+
"rstrip": false,
|
300 |
+
"normalized": true,
|
301 |
+
"special": false
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"id": 33,
|
305 |
+
"content": "33 ",
|
306 |
+
"single_word": false,
|
307 |
+
"lstrip": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"normalized": true,
|
310 |
+
"special": false
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"id": 34,
|
314 |
+
"content": "34 ",
|
315 |
+
"single_word": false,
|
316 |
+
"lstrip": false,
|
317 |
+
"rstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"special": false
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"id": 35,
|
323 |
+
"content": "35 ",
|
324 |
+
"single_word": false,
|
325 |
+
"lstrip": false,
|
326 |
+
"rstrip": false,
|
327 |
+
"normalized": true,
|
328 |
+
"special": false
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"id": 36,
|
332 |
+
"content": "36 ",
|
333 |
+
"single_word": false,
|
334 |
+
"lstrip": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"normalized": true,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"id": 37,
|
341 |
+
"content": "37 ",
|
342 |
+
"single_word": false,
|
343 |
+
"lstrip": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"normalized": true,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"id": 38,
|
350 |
+
"content": "38 ",
|
351 |
+
"single_word": false,
|
352 |
+
"lstrip": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"normalized": true,
|
355 |
+
"special": false
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"id": 39,
|
359 |
+
"content": "39 ",
|
360 |
+
"single_word": false,
|
361 |
+
"lstrip": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"normalized": true,
|
364 |
+
"special": false
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"id": 40,
|
368 |
+
"content": "40 ",
|
369 |
+
"single_word": false,
|
370 |
+
"lstrip": false,
|
371 |
+
"rstrip": false,
|
372 |
+
"normalized": true,
|
373 |
+
"special": false
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"id": 41,
|
377 |
+
"content": "41 ",
|
378 |
+
"single_word": false,
|
379 |
+
"lstrip": false,
|
380 |
+
"rstrip": false,
|
381 |
+
"normalized": true,
|
382 |
+
"special": false
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"id": 42,
|
386 |
+
"content": "42 ",
|
387 |
+
"single_word": false,
|
388 |
+
"lstrip": false,
|
389 |
+
"rstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"special": false
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"id": 43,
|
395 |
+
"content": "43 ",
|
396 |
+
"single_word": false,
|
397 |
+
"lstrip": false,
|
398 |
+
"rstrip": false,
|
399 |
+
"normalized": true,
|
400 |
+
"special": false
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"id": 44,
|
404 |
+
"content": "44 ",
|
405 |
+
"single_word": false,
|
406 |
+
"lstrip": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"normalized": true,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"id": 45,
|
413 |
+
"content": "45 ",
|
414 |
+
"single_word": false,
|
415 |
+
"lstrip": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"normalized": true,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"id": 46,
|
422 |
+
"content": "46 ",
|
423 |
+
"single_word": false,
|
424 |
+
"lstrip": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"normalized": true,
|
427 |
+
"special": false
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"id": 47,
|
431 |
+
"content": "47 ",
|
432 |
+
"single_word": false,
|
433 |
+
"lstrip": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"normalized": true,
|
436 |
+
"special": false
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"id": 48,
|
440 |
+
"content": "48 ",
|
441 |
+
"single_word": false,
|
442 |
+
"lstrip": false,
|
443 |
+
"rstrip": false,
|
444 |
+
"normalized": true,
|
445 |
+
"special": false
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"id": 49,
|
449 |
+
"content": "49 ",
|
450 |
+
"single_word": false,
|
451 |
+
"lstrip": false,
|
452 |
+
"rstrip": false,
|
453 |
+
"normalized": true,
|
454 |
+
"special": false
|
455 |
}
|
456 |
],
|
457 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -16,6 +16,390 @@
|
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
},
|
21 |
"bos_token": "0 ",
|
|
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "2 ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "3 ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "4 ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": "5 ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": "6 ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "7 ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "8 ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "9 ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "10 ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "11 ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"12": {
|
101 |
+
"content": "12 ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"13": {
|
109 |
+
"content": "13 ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"14": {
|
117 |
+
"content": "14 ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"15": {
|
125 |
+
"content": "15 ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"16": {
|
133 |
+
"content": "16 ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"17": {
|
141 |
+
"content": "17 ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"18": {
|
149 |
+
"content": "18 ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"19": {
|
157 |
+
"content": "19 ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"20": {
|
165 |
+
"content": "20 ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"21": {
|
173 |
+
"content": "21 ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"22": {
|
181 |
+
"content": "22 ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"23": {
|
189 |
+
"content": "23 ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"24": {
|
197 |
+
"content": "24 ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"25": {
|
205 |
+
"content": "25 ",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"26": {
|
213 |
+
"content": "26 ",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"27": {
|
221 |
+
"content": "27 ",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"28": {
|
229 |
+
"content": "28 ",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"29": {
|
237 |
+
"content": "29 ",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"30": {
|
245 |
+
"content": "30 ",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"31": {
|
253 |
+
"content": "31 ",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"32": {
|
261 |
+
"content": "32 ",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"33": {
|
269 |
+
"content": "33 ",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"34": {
|
277 |
+
"content": "34 ",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"35": {
|
285 |
+
"content": "35 ",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"36": {
|
293 |
+
"content": "36 ",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"37": {
|
301 |
+
"content": "37 ",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"38": {
|
309 |
+
"content": "38 ",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"39": {
|
317 |
+
"content": "39 ",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": true,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"40": {
|
325 |
+
"content": "40 ",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": true,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"41": {
|
333 |
+
"content": "41 ",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": true,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"42": {
|
341 |
+
"content": "42 ",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": true,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"43": {
|
349 |
+
"content": "43 ",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": true,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"44": {
|
357 |
+
"content": "44 ",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": true,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"45": {
|
365 |
+
"content": "45 ",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": true,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"46": {
|
373 |
+
"content": "46 ",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": true,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"47": {
|
381 |
+
"content": "47 ",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": true,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"48": {
|
389 |
+
"content": "48 ",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"49": {
|
397 |
+
"content": "49 ",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": true,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
}
|
404 |
},
|
405 |
"bos_token": "0 ",
|