Upload folder using huggingface_hub
Browse files
fw57Mmulti_Surprisal_thresholdB_16000/tokenizer.json
CHANGED
@@ -58,518 +58,518 @@
|
|
58 |
"vocab": {
|
59 |
"<|padding|>": 0,
|
60 |
"<|endoftext|>": 1,
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
72 |
-
"
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"
|
79 |
-
"
|
80 |
-
"
|
81 |
-
"
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
"
|
91 |
-
"
|
92 |
-
"
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"
|
96 |
-
"
|
97 |
-
"
|
98 |
-
"##
|
99 |
-
"
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"
|
103 |
-
"
|
104 |
-
"
|
105 |
-
"
|
106 |
-
"
|
107 |
-
"
|
108 |
-
"
|
109 |
-
"
|
110 |
-
"##
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"Ġ
|
134 |
-
"##
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
156 |
-
"##
|
157 |
-
"
|
158 |
-
"
|
159 |
-
"
|
160 |
-
"
|
161 |
-
"
|
162 |
-
"
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"
|
166 |
-
"
|
167 |
-
"
|
168 |
-
"
|
169 |
-
"
|
170 |
-
"
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"##
|
179 |
-
"
|
180 |
-
"
|
181 |
-
"
|
182 |
-
"
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"
|
187 |
-
"
|
188 |
-
"
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"
|
193 |
-
"
|
194 |
-
"
|
195 |
-
"
|
196 |
-
"
|
197 |
-
"
|
198 |
-
"
|
199 |
-
"
|
200 |
-
"
|
201 |
-
"
|
202 |
-
"
|
203 |
-
"
|
204 |
-
"
|
205 |
-
"
|
206 |
-
"
|
207 |
-
"
|
208 |
-
"
|
209 |
-
"
|
210 |
-
"
|
211 |
-
"
|
212 |
-
"
|
213 |
-
"
|
214 |
-
"
|
215 |
-
"
|
216 |
-
"
|
217 |
-
"
|
218 |
-
"
|
219 |
-
"
|
220 |
-
"
|
221 |
-
"
|
222 |
-
"
|
223 |
-
"
|
224 |
-
"##
|
225 |
-
"
|
226 |
-
"
|
227 |
-
"
|
228 |
-
"##
|
229 |
-
"
|
230 |
-
"
|
231 |
-
"
|
232 |
-
"
|
233 |
-
"
|
234 |
-
"
|
235 |
-
"
|
236 |
-
"
|
237 |
-
"
|
238 |
-
"
|
239 |
-
"
|
240 |
-
"
|
241 |
-
"
|
242 |
-
"
|
243 |
-
"
|
244 |
-
"
|
245 |
-
"
|
246 |
-
"
|
247 |
-
"
|
248 |
-
"
|
249 |
-
"
|
250 |
-
"
|
251 |
-
"
|
252 |
-
"
|
253 |
-
"
|
254 |
-
"
|
255 |
-
"
|
256 |
-
"
|
257 |
-
"
|
258 |
-
"##
|
259 |
-
"
|
260 |
-
"
|
261 |
-
"
|
262 |
-
"
|
263 |
-
"
|
264 |
-
"
|
265 |
-
"
|
266 |
-
"
|
267 |
-
"
|
268 |
-
"
|
269 |
-
"
|
270 |
-
"
|
271 |
-
"
|
272 |
-
"
|
273 |
-
"
|
274 |
-
"##
|
275 |
-
"
|
276 |
-
"
|
277 |
-
"
|
278 |
-
"
|
279 |
-
"
|
280 |
-
"
|
281 |
-
"
|
282 |
-
"
|
283 |
-
"
|
284 |
-
"
|
285 |
-
"
|
286 |
-
"
|
287 |
-
"
|
288 |
-
"
|
289 |
-
"
|
290 |
-
"
|
291 |
-
"
|
292 |
-
"
|
293 |
-
"
|
294 |
-
"
|
295 |
-
"
|
296 |
-
"
|
297 |
-
"
|
298 |
-
"
|
299 |
-
"
|
300 |
-
"##
|
301 |
-
"
|
302 |
-
"
|
303 |
-
"
|
304 |
-
"
|
305 |
-
"
|
306 |
-
"
|
307 |
-
"
|
308 |
-
"
|
309 |
-
"
|
310 |
-
"
|
311 |
-
"
|
312 |
-
"
|
313 |
-
"
|
314 |
-
"##
|
315 |
-
"
|
316 |
-
"
|
317 |
-
"
|
318 |
-
"
|
319 |
-
"
|
320 |
-
"
|
321 |
-
"
|
322 |
-
"
|
323 |
-
"
|
324 |
-
"##
|
325 |
-
"
|
326 |
-
"
|
327 |
-
"
|
328 |
-
"
|
329 |
-
"
|
330 |
-
"
|
331 |
-
"
|
332 |
-
"
|
333 |
-
"
|
334 |
-
"
|
335 |
-
"
|
336 |
-
"
|
337 |
-
"
|
338 |
-
"
|
339 |
-
"
|
340 |
-
"
|
341 |
-
"
|
342 |
-
"
|
343 |
-
"
|
344 |
-
"
|
345 |
-
"
|
346 |
-
"
|
347 |
-
"
|
348 |
-
"
|
349 |
-
"
|
350 |
-
"##
|
351 |
-
"
|
352 |
-
"
|
353 |
-
"
|
354 |
-
"
|
355 |
-
"
|
356 |
-
"
|
357 |
-
"
|
358 |
-
"
|
359 |
-
"
|
360 |
-
"
|
361 |
-
"
|
362 |
-
"##
|
363 |
-
"
|
364 |
-
"
|
365 |
-
"
|
366 |
-
"
|
367 |
-
"
|
368 |
-
"
|
369 |
-
"
|
370 |
-
"
|
371 |
-
"
|
372 |
-
"
|
373 |
-
"
|
374 |
-
"
|
375 |
-
"
|
376 |
-
"
|
377 |
-
"
|
378 |
-
"
|
379 |
-
"
|
380 |
-
"
|
381 |
-
"
|
382 |
-
"
|
383 |
-
"
|
384 |
-
"
|
385 |
-
"
|
386 |
-
"
|
387 |
-
"
|
388 |
-
"
|
389 |
-
"
|
390 |
-
"
|
391 |
-
"
|
392 |
-
"
|
393 |
-
"
|
394 |
-
"
|
395 |
-
"
|
396 |
-
"
|
397 |
-
"
|
398 |
-
"##
|
399 |
-
"
|
400 |
-
"
|
401 |
-
"
|
402 |
-
"
|
403 |
-
"
|
404 |
-
"
|
405 |
-
"
|
406 |
-
"
|
407 |
-
"
|
408 |
-
"
|
409 |
-
"
|
410 |
-
"
|
411 |
-
"
|
412 |
-
"
|
413 |
-
"
|
414 |
-
"
|
415 |
-
"
|
416 |
-
"##
|
417 |
-
"
|
418 |
-
"
|
419 |
-
"
|
420 |
-
"
|
421 |
-
"
|
422 |
-
"
|
423 |
-
"
|
424 |
-
"
|
425 |
-
"
|
426 |
-
"
|
427 |
-
"
|
428 |
-
"
|
429 |
-
"
|
430 |
-
"
|
431 |
-
"
|
432 |
-
"
|
433 |
-
"
|
434 |
-
"
|
435 |
-
"
|
436 |
-
"
|
437 |
-
"
|
438 |
-
"##
|
439 |
-
"
|
440 |
-
"
|
441 |
-
"
|
442 |
-
"
|
443 |
-
"
|
444 |
-
"
|
445 |
-
"
|
446 |
-
"
|
447 |
-
"
|
448 |
-
"
|
449 |
-
"
|
450 |
-
"
|
451 |
-
"
|
452 |
-
"
|
453 |
-
"
|
454 |
-
"
|
455 |
-
"
|
456 |
-
"
|
457 |
-
"
|
458 |
-
"
|
459 |
-
"
|
460 |
-
"
|
461 |
-
"
|
462 |
-
"
|
463 |
-
"
|
464 |
-
"
|
465 |
-
"
|
466 |
-
"
|
467 |
-
"
|
468 |
-
"
|
469 |
-
"
|
470 |
-
"
|
471 |
-
"
|
472 |
-
"
|
473 |
-
"
|
474 |
-
"
|
475 |
-
"
|
476 |
-
"
|
477 |
-
"
|
478 |
-
"
|
479 |
-
"
|
480 |
-
"
|
481 |
-
"
|
482 |
-
"
|
483 |
-
"
|
484 |
-
"
|
485 |
-
"
|
486 |
-
"
|
487 |
-
"
|
488 |
-
"
|
489 |
-
"
|
490 |
-
"
|
491 |
-
"
|
492 |
-
"
|
493 |
-
"
|
494 |
-
"
|
495 |
-
"
|
496 |
-
"
|
497 |
-
"
|
498 |
-
"##
|
499 |
-
"
|
500 |
-
"
|
501 |
-
"
|
502 |
-
"
|
503 |
-
"
|
504 |
-
"
|
505 |
-
"
|
506 |
-
"
|
507 |
-
"
|
508 |
-
"
|
509 |
-
"
|
510 |
-
"
|
511 |
-
"
|
512 |
-
"##
|
513 |
-
"
|
514 |
-
"
|
515 |
-
"
|
516 |
-
"
|
517 |
-
"
|
518 |
-
"
|
519 |
-
"
|
520 |
-
"
|
521 |
-
"
|
522 |
-
"
|
523 |
-
"
|
524 |
-
"
|
525 |
-
"
|
526 |
-
"
|
527 |
-
"
|
528 |
-
"##
|
529 |
-
"
|
530 |
-
"
|
531 |
-
"
|
532 |
-
"
|
533 |
-
"
|
534 |
-
"
|
535 |
-
"
|
536 |
-
"
|
537 |
-
"
|
538 |
-
"
|
539 |
-
"
|
540 |
-
"
|
541 |
-
"
|
542 |
-
"
|
543 |
-
"
|
544 |
-
"
|
545 |
-
"
|
546 |
-
"
|
547 |
-
"
|
548 |
-
"
|
549 |
-
"
|
550 |
-
"
|
551 |
-
"
|
552 |
-
"
|
553 |
-
"
|
554 |
-
"
|
555 |
-
"
|
556 |
-
"
|
557 |
-
"
|
558 |
-
"
|
559 |
-
"
|
560 |
-
"
|
561 |
-
"
|
562 |
-
"
|
563 |
-
"
|
564 |
-
"
|
565 |
-
"
|
566 |
-
"##
|
567 |
-
"
|
568 |
-
"
|
569 |
-
"
|
570 |
-
"
|
571 |
-
"
|
572 |
-
"
|
573 |
"<|unk|>": 514,
|
574 |
"##�": 515,
|
575 |
"Ġsa": 516,
|
|
|
58 |
"vocab": {
|
59 |
"<|padding|>": 0,
|
60 |
"<|endoftext|>": 1,
|
61 |
+
"ĠŁ": 2,
|
62 |
+
"##Ł": 3,
|
63 |
+
"Ġč": 4,
|
64 |
+
"##č": 5,
|
65 |
+
"Ġ^": 6,
|
66 |
+
"##^": 7,
|
67 |
+
"Ġ<": 8,
|
68 |
+
"##<": 9,
|
69 |
+
"Ġr": 10,
|
70 |
+
"##r": 11,
|
71 |
+
"Ġĺ": 12,
|
72 |
+
"##ĺ": 13,
|
73 |
+
"ĠĄ": 14,
|
74 |
+
"##Ą": 15,
|
75 |
+
"Ġ'": 16,
|
76 |
+
"##'": 17,
|
77 |
+
"Ġij": 18,
|
78 |
+
"##ij": 19,
|
79 |
+
"Ġ,": 20,
|
80 |
+
"##,": 21,
|
81 |
+
"ĠĬ": 22,
|
82 |
+
"##Ĭ": 23,
|
83 |
+
"Ġ4": 24,
|
84 |
+
"##4": 25,
|
85 |
+
"Ġª": 26,
|
86 |
+
"##ª": 27,
|
87 |
+
"Ġĕ": 28,
|
88 |
+
"##ĕ": 29,
|
89 |
+
"Ġį": 30,
|
90 |
+
"##į": 31,
|
91 |
+
"Ġº": 32,
|
92 |
+
"##º": 33,
|
93 |
+
"Ġã": 34,
|
94 |
+
"##ã": 35,
|
95 |
+
"Ġý": 36,
|
96 |
+
"##ý": 37,
|
97 |
+
"Ġ_": 38,
|
98 |
+
"##_": 39,
|
99 |
+
"Ġä": 40,
|
100 |
+
"##ä": 41,
|
101 |
+
"Ġ`": 42,
|
102 |
+
"##`": 43,
|
103 |
+
"Ġþ": 44,
|
104 |
+
"##þ": 45,
|
105 |
+
"Ġđ": 46,
|
106 |
+
"##đ": 47,
|
107 |
+
"Ġò": 48,
|
108 |
+
"##ò": 49,
|
109 |
+
"Ġ9": 50,
|
110 |
+
"##9": 51,
|
111 |
+
"Ġú": 52,
|
112 |
+
"##ú": 53,
|
113 |
+
"Ġķ": 54,
|
114 |
+
"##ķ": 55,
|
115 |
+
"Ġĵ": 56,
|
116 |
+
"##ĵ": 57,
|
117 |
+
"ĠĘ": 58,
|
118 |
+
"##Ę": 59,
|
119 |
+
"Ġġ": 60,
|
120 |
+
"##ġ": 61,
|
121 |
+
"Ġ¤": 62,
|
122 |
+
"##¤": 63,
|
123 |
+
"ĠÐ": 64,
|
124 |
+
"##Ð": 65,
|
125 |
+
"Ġâ": 66,
|
126 |
+
"##â": 67,
|
127 |
+
"ĠĿ": 68,
|
128 |
+
"##Ŀ": 69,
|
129 |
+
"Ġß": 70,
|
130 |
+
"##ß": 71,
|
131 |
+
"ĠÀ": 72,
|
132 |
+
"##À": 73,
|
133 |
+
"Ġ[": 74,
|
134 |
+
"##[": 75,
|
135 |
+
"Ġw": 76,
|
136 |
+
"##w": 77,
|
137 |
+
"Ġ|": 78,
|
138 |
+
"##|": 79,
|
139 |
+
"Ġī": 80,
|
140 |
+
"##ī": 81,
|
141 |
+
"Ġ$": 82,
|
142 |
+
"##$": 83,
|
143 |
+
"Ġì": 84,
|
144 |
+
"##ì": 85,
|
145 |
+
"Ġ£": 86,
|
146 |
+
"##£": 87,
|
147 |
+
"Ġ2": 88,
|
148 |
+
"##2": 89,
|
149 |
+
"ĠÏ": 90,
|
150 |
+
"##Ï": 91,
|
151 |
+
"Ġ«": 92,
|
152 |
+
"##«": 93,
|
153 |
+
"ĠN": 94,
|
154 |
+
"##N": 95,
|
155 |
+
"ĠF": 96,
|
156 |
+
"##F": 97,
|
157 |
+
"Ġ¼": 98,
|
158 |
+
"##¼": 99,
|
159 |
+
"Ġ-": 100,
|
160 |
+
"##-": 101,
|
161 |
+
"ĠĽ": 102,
|
162 |
+
"##Ľ": 103,
|
163 |
+
"Ġ½": 104,
|
164 |
+
"##½": 105,
|
165 |
+
"Ġð": 106,
|
166 |
+
"##ð": 107,
|
167 |
+
"Ġ©": 108,
|
168 |
+
"##©": 109,
|
169 |
+
"ĠÂ": 110,
|
170 |
+
"##Â": 111,
|
171 |
+
"Ġę": 112,
|
172 |
+
"##ę": 113,
|
173 |
+
"Ġc": 114,
|
174 |
+
"##c": 115,
|
175 |
+
"ĠA": 116,
|
176 |
+
"##A": 117,
|
177 |
+
"Ġo": 118,
|
178 |
+
"##o": 119,
|
179 |
+
"ĠÄ": 120,
|
180 |
+
"##Ä": 121,
|
181 |
+
"Ġ¸": 122,
|
182 |
+
"##¸": 123,
|
183 |
+
"ĠĪ": 124,
|
184 |
+
"##Ī": 125,
|
185 |
+
"Ġě": 126,
|
186 |
+
"##ě": 127,
|
187 |
+
"Ġñ": 128,
|
188 |
+
"##ñ": 129,
|
189 |
+
"Ġă": 130,
|
190 |
+
"##ă": 131,
|
191 |
+
"Ġn": 132,
|
192 |
+
"##n": 133,
|
193 |
+
"Ġæ": 134,
|
194 |
+
"##æ": 135,
|
195 |
+
"Ġ¨": 136,
|
196 |
+
"##¨": 137,
|
197 |
+
"ĠÚ": 138,
|
198 |
+
"##Ú": 139,
|
199 |
+
"Ġ1": 140,
|
200 |
+
"##1": 141,
|
201 |
+
"Ġç": 142,
|
202 |
+
"##ç": 143,
|
203 |
+
"Ġą": 144,
|
204 |
+
"##ą": 145,
|
205 |
+
"Ġb": 146,
|
206 |
+
"##b": 147,
|
207 |
+
"ĠM": 148,
|
208 |
+
"##M": 149,
|
209 |
+
"ĠÛ": 150,
|
210 |
+
"##Û": 151,
|
211 |
+
"Ġğ": 152,
|
212 |
+
"##ğ": 153,
|
213 |
+
"ĠĢ": 154,
|
214 |
+
"##Ģ": 155,
|
215 |
+
"Ġ#": 156,
|
216 |
+
"###": 157,
|
217 |
+
"Ġ\"": 158,
|
218 |
+
"##\"": 159,
|
219 |
+
"Ġi": 160,
|
220 |
+
"##i": 161,
|
221 |
+
"Ġı": 162,
|
222 |
+
"##ı": 163,
|
223 |
+
"ĠH": 164,
|
224 |
+
"##H": 165,
|
225 |
+
"ĠË": 166,
|
226 |
+
"##Ë": 167,
|
227 |
+
"Ġj": 168,
|
228 |
+
"##j": 169,
|
229 |
+
"ĠÌ": 170,
|
230 |
+
"##Ì": 171,
|
231 |
+
"ĠĎ": 172,
|
232 |
+
"##Ď": 173,
|
233 |
+
"ĠĐ": 174,
|
234 |
+
"##Đ": 175,
|
235 |
+
"ĠQ": 176,
|
236 |
+
"##Q": 177,
|
237 |
+
"ĠĆ": 178,
|
238 |
+
"##Ć": 179,
|
239 |
+
"ĠĶ": 180,
|
240 |
+
"##Ķ": 181,
|
241 |
+
"Ġ6": 182,
|
242 |
+
"##6": 183,
|
243 |
+
"ĠČ": 184,
|
244 |
+
"##Č": 185,
|
245 |
+
"Ġ7": 186,
|
246 |
+
"##7": 187,
|
247 |
+
"Ġć": 188,
|
248 |
+
"##ć": 189,
|
249 |
+
"Ġ=": 190,
|
250 |
+
"##=": 191,
|
251 |
+
"Ġĭ": 192,
|
252 |
+
"##ĭ": 193,
|
253 |
+
"Ġ´": 194,
|
254 |
+
"##´": 195,
|
255 |
+
"ĠJ": 196,
|
256 |
+
"##J": 197,
|
257 |
+
"ĠW": 198,
|
258 |
+
"##W": 199,
|
259 |
+
"ĠĴ": 200,
|
260 |
+
"##Ĵ": 201,
|
261 |
+
"Ġ+": 202,
|
262 |
+
"##+": 203,
|
263 |
+
"Ġ§": 204,
|
264 |
+
"##§": 205,
|
265 |
+
"Ġĩ": 206,
|
266 |
+
"##ĩ": 207,
|
267 |
+
"Ġk": 208,
|
268 |
+
"##k": 209,
|
269 |
+
"Ġ¢": 210,
|
270 |
+
"##¢": 211,
|
271 |
+
"Ġx": 212,
|
272 |
+
"##x": 213,
|
273 |
+
"ĠI": 214,
|
274 |
+
"##I": 215,
|
275 |
+
"Ġ³": 216,
|
276 |
+
"##³": 217,
|
277 |
+
"Ġ5": 218,
|
278 |
+
"##5": 219,
|
279 |
+
"Ġ¿": 220,
|
280 |
+
"##¿": 221,
|
281 |
+
"Ġï": 222,
|
282 |
+
"##ï": 223,
|
283 |
+
"ĠÁ": 224,
|
284 |
+
"##Á": 225,
|
285 |
+
"ĠĦ": 226,
|
286 |
+
"##Ħ": 227,
|
287 |
+
"ĠĔ": 228,
|
288 |
+
"##Ĕ": 229,
|
289 |
+
"ĠĒ": 230,
|
290 |
+
"##Ē": 231,
|
291 |
+
"ĠÔ": 232,
|
292 |
+
"##Ô": 233,
|
293 |
+
"Ġ°": 234,
|
294 |
+
"##°": 235,
|
295 |
+
"ĠĜ": 236,
|
296 |
+
"##Ĝ": 237,
|
297 |
+
"Ġ:": 238,
|
298 |
+
"##:": 239,
|
299 |
+
"ĠR": 240,
|
300 |
+
"##R": 241,
|
301 |
+
"Ġ0": 242,
|
302 |
+
"##0": 243,
|
303 |
+
"Ġz": 244,
|
304 |
+
"##z": 245,
|
305 |
+
"ĠĮ": 246,
|
306 |
+
"##Į": 247,
|
307 |
+
"Ġľ": 248,
|
308 |
+
"##ľ": 249,
|
309 |
+
"ĠT": 250,
|
310 |
+
"##T": 251,
|
311 |
+
"Ġh": 252,
|
312 |
+
"##h": 253,
|
313 |
+
"Ġf": 254,
|
314 |
+
"##f": 255,
|
315 |
+
"ĠG": 256,
|
316 |
+
"##G": 257,
|
317 |
+
"ĠÎ": 258,
|
318 |
+
"##Î": 259,
|
319 |
+
"Ġ¬": 260,
|
320 |
+
"##¬": 261,
|
321 |
+
"ĠØ": 262,
|
322 |
+
"##Ø": 263,
|
323 |
+
"ĠL": 264,
|
324 |
+
"##L": 265,
|
325 |
+
"Ġ¦": 266,
|
326 |
+
"##¦": 267,
|
327 |
+
"Ġ>": 268,
|
328 |
+
"##>": 269,
|
329 |
+
"ĠÞ": 270,
|
330 |
+
"##Þ": 271,
|
331 |
+
"Ġy": 272,
|
332 |
+
"##y": 273,
|
333 |
+
"ĠÊ": 274,
|
334 |
+
"##Ê": 275,
|
335 |
+
"Ġg": 276,
|
336 |
+
"##g": 277,
|
337 |
+
"Ġö": 278,
|
338 |
+
"##ö": 279,
|
339 |
+
"Ġł": 280,
|
340 |
+
"##ł": 281,
|
341 |
+
"Ġ.": 282,
|
342 |
+
"##.": 283,
|
343 |
+
"Ġď": 284,
|
344 |
+
"##ď": 285,
|
345 |
+
"ĠÜ": 286,
|
346 |
+
"##Ü": 287,
|
347 |
+
"ĠU": 288,
|
348 |
+
"##U": 289,
|
349 |
+
"Ġv": 290,
|
350 |
+
"##v": 291,
|
351 |
+
"Ġî": 292,
|
352 |
+
"##î": 293,
|
353 |
+
"Ġ/": 294,
|
354 |
+
"##/": 295,
|
355 |
+
"ĠĀ": 296,
|
356 |
+
"##Ā": 297,
|
357 |
+
"Ġm": 298,
|
358 |
+
"##m": 299,
|
359 |
+
"Ġu": 300,
|
360 |
+
"##u": 301,
|
361 |
+
"Ġ)": 302,
|
362 |
+
"##)": 303,
|
363 |
+
"Ġ¯": 304,
|
364 |
+
"##¯": 305,
|
365 |
+
"Ġê": 306,
|
366 |
+
"##ê": 307,
|
367 |
+
"Ġÿ": 308,
|
368 |
+
"##ÿ": 309,
|
369 |
+
"ĠĖ": 310,
|
370 |
+
"##Ė": 311,
|
371 |
+
"Ġİ": 312,
|
372 |
+
"##İ": 313,
|
373 |
+
"ĠC": 314,
|
374 |
+
"##C": 315,
|
375 |
+
"Ġù": 316,
|
376 |
+
"##ù": 317,
|
377 |
+
"Ġā": 318,
|
378 |
+
"##ā": 319,
|
379 |
+
"ĠD": 320,
|
380 |
+
"##D": 321,
|
381 |
+
"Ġ?": 322,
|
382 |
+
"##?": 323,
|
383 |
+
"ĠY": 324,
|
384 |
+
"##Y": 325,
|
385 |
+
"Ġė": 326,
|
386 |
+
"##ė": 327,
|
387 |
+
"ĠS": 328,
|
388 |
+
"##S": 329,
|
389 |
+
"Ġ(": 330,
|
390 |
+
"##(": 331,
|
391 |
+
"Ġ}": 332,
|
392 |
+
"##}": 333,
|
393 |
+
"Ġ¹": 334,
|
394 |
+
"##¹": 335,
|
395 |
+
"ĠÝ": 336,
|
396 |
+
"##Ý": 337,
|
397 |
+
"Ġp": 338,
|
398 |
+
"##p": 339,
|
399 |
+
"Ġü": 340,
|
400 |
+
"##ü": 341,
|
401 |
+
"ĠÇ": 342,
|
402 |
+
"##Ç": 343,
|
403 |
+
"Ġt": 344,
|
404 |
+
"##t": 345,
|
405 |
+
"ĠÅ": 346,
|
406 |
+
"##Å": 347,
|
407 |
+
"Ġċ": 348,
|
408 |
+
"##ċ": 349,
|
409 |
+
"Ġ;": 350,
|
410 |
+
"##;": 351,
|
411 |
+
"ĠÒ": 352,
|
412 |
+
"##Ò": 353,
|
413 |
+
"Ġû": 354,
|
414 |
+
"##û": 355,
|
415 |
+
"Ġl": 356,
|
416 |
+
"##l": 357,
|
417 |
+
"ĠE": 358,
|
418 |
+
"##E": 359,
|
419 |
+
"Ġí": 360,
|
420 |
+
"##í": 361,
|
421 |
+
"ĠĂ": 362,
|
422 |
+
"##Ă": 363,
|
423 |
+
"ĠĈ": 364,
|
424 |
+
"##Ĉ": 365,
|
425 |
+
"Ġŀ": 366,
|
426 |
+
"##ŀ": 367,
|
427 |
+
"Ġá": 368,
|
428 |
+
"##á": 369,
|
429 |
+
"ĠŃ": 370,
|
430 |
+
"##Ń": 371,
|
431 |
+
"Ġ®": 372,
|
432 |
+
"##®": 373,
|
433 |
+
"Ġ±": 374,
|
434 |
+
"##±": 375,
|
435 |
+
"Ġ¥": 376,
|
436 |
+
"##¥": 377,
|
437 |
+
"Ġd": 378,
|
438 |
+
"##d": 379,
|
439 |
+
"ĠÙ": 380,
|
440 |
+
"##Ù": 381,
|
441 |
+
"Ġ¡": 382,
|
442 |
+
"##¡": 383,
|
443 |
+
"ĠÈ": 384,
|
444 |
+
"##È": 385,
|
445 |
+
"Ġ!": 386,
|
446 |
+
"##!": 387,
|
447 |
+
"Ġ~": 388,
|
448 |
+
"##~": 389,
|
449 |
+
"Ġ3": 390,
|
450 |
+
"##3": 391,
|
451 |
+
"Ġ×": 392,
|
452 |
+
"##×": 393,
|
453 |
+
"Ġ÷": 394,
|
454 |
+
"##÷": 395,
|
455 |
+
"Ġe": 396,
|
456 |
+
"##e": 397,
|
457 |
+
"Ġ]": 398,
|
458 |
+
"##]": 399,
|
459 |
+
"Ġå": 400,
|
460 |
+
"##å": 401,
|
461 |
+
"ĠĊ": 402,
|
462 |
+
"##Ċ": 403,
|
463 |
+
"Ġô": 404,
|
464 |
+
"##ô": 405,
|
465 |
+
"ĠĹ": 406,
|
466 |
+
"##Ĺ": 407,
|
467 |
+
"ĠĞ": 408,
|
468 |
+
"##Ğ": 409,
|
469 |
+
"Ġĥ": 410,
|
470 |
+
"##ĥ": 411,
|
471 |
+
"ĠĚ": 412,
|
472 |
+
"##Ě": 413,
|
473 |
+
"Ġë": 414,
|
474 |
+
"##ë": 415,
|
475 |
+
"Ġ²": 416,
|
476 |
+
"##²": 417,
|
477 |
+
"Ġà": 418,
|
478 |
+
"##à": 419,
|
479 |
+
"ĠĨ": 420,
|
480 |
+
"##Ĩ": 421,
|
481 |
+
"ĠÑ": 422,
|
482 |
+
"##Ñ": 423,
|
483 |
+
"ĠV": 424,
|
484 |
+
"##V": 425,
|
485 |
+
"Ġµ": 426,
|
486 |
+
"##µ": 427,
|
487 |
+
"Ġĸ": 428,
|
488 |
+
"##ĸ": 429,
|
489 |
+
"Ġ»": 430,
|
490 |
+
"##»": 431,
|
491 |
+
"Ġõ": 432,
|
492 |
+
"##õ": 433,
|
493 |
+
"ĠĻ": 434,
|
494 |
+
"##Ļ": 435,
|
495 |
+
"Ġè": 436,
|
496 |
+
"##è": 437,
|
497 |
+
"ĠO": 438,
|
498 |
+
"##O": 439,
|
499 |
+
"Ġĉ": 440,
|
500 |
+
"##ĉ": 441,
|
501 |
+
"ĠÓ": 442,
|
502 |
+
"##Ó": 443,
|
503 |
+
"Ġø": 444,
|
504 |
+
"##ø": 445,
|
505 |
+
"Ġ·": 446,
|
506 |
+
"##·": 447,
|
507 |
+
"ĠK": 448,
|
508 |
+
"##K": 449,
|
509 |
+
"ĠÍ": 450,
|
510 |
+
"##Í": 451,
|
511 |
+
"Ġa": 452,
|
512 |
+
"##a": 453,
|
513 |
+
"ĠZ": 454,
|
514 |
+
"##Z": 455,
|
515 |
+
"ĠX": 456,
|
516 |
+
"##X": 457,
|
517 |
+
"ĠÕ": 458,
|
518 |
+
"##Õ": 459,
|
519 |
+
"Ġ@": 460,
|
520 |
+
"##@": 461,
|
521 |
+
"Ġ%": 462,
|
522 |
+
"##%": 463,
|
523 |
+
"Ġ*": 464,
|
524 |
+
"##*": 465,
|
525 |
+
"Ġs": 466,
|
526 |
+
"##s": 467,
|
527 |
+
"ĠP": 468,
|
528 |
+
"##P": 469,
|
529 |
+
"Ġħ": 470,
|
530 |
+
"##ħ": 471,
|
531 |
+
"Ġļ": 472,
|
532 |
+
"##ļ": 473,
|
533 |
+
"Ġé": 474,
|
534 |
+
"##é": 475,
|
535 |
+
"Ġē": 476,
|
536 |
+
"##ē": 477,
|
537 |
+
"ĠB": 478,
|
538 |
+
"##B": 479,
|
539 |
+
"Ġ{": 480,
|
540 |
+
"##{": 481,
|
541 |
+
"Ġ&": 482,
|
542 |
+
"##&": 483,
|
543 |
+
"ĠÉ": 484,
|
544 |
+
"##É": 485,
|
545 |
+
"Ġģ": 486,
|
546 |
+
"##ģ": 487,
|
547 |
+
"ĠIJ": 488,
|
548 |
+
"##IJ": 489,
|
549 |
+
"Ġ¾": 490,
|
550 |
+
"##¾": 491,
|
551 |
+
"ĠÖ": 492,
|
552 |
+
"##Ö": 493,
|
553 |
+
"Ġ¶": 494,
|
554 |
+
"##¶": 495,
|
555 |
+
"Ġó": 496,
|
556 |
+
"##ó": 497,
|
557 |
+
"Ġ\\": 498,
|
558 |
+
"##\\": 499,
|
559 |
+
"Ġĝ": 500,
|
560 |
+
"##ĝ": 501,
|
561 |
+
"ĠĤ": 502,
|
562 |
+
"##Ĥ": 503,
|
563 |
+
"Ġ8": 504,
|
564 |
+
"##8": 505,
|
565 |
+
"Ġq": 506,
|
566 |
+
"##q": 507,
|
567 |
+
"ĠÃ": 508,
|
568 |
+
"##Ã": 509,
|
569 |
+
"ĠÆ": 510,
|
570 |
+
"##Æ": 511,
|
571 |
+
"ĠĠ": 512,
|
572 |
+
"##Ġ": 513,
|
573 |
"<|unk|>": 514,
|
574 |
"##�": 515,
|
575 |
"Ġsa": 516,
|
fw57Mmulti_Surprisal_thresholdB_16000/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|