Update tiny models for CLIPForImageClassification
#45
by
hf-transformers-bot
- opened
- config.json +1 -1
- model.safetensors +1 -1
- preprocessor_config.json +17 -0
- tokenizer.json +129 -129
- vocab.json +129 -129
config.json
CHANGED
@@ -24,7 +24,7 @@
|
|
24 |
"vocab_size": 1024
|
25 |
},
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"vision_config": {
|
29 |
"attention_dropout": 0.1,
|
30 |
"dropout": 0.1,
|
|
|
24 |
"vocab_size": 1024
|
25 |
},
|
26 |
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.40.0.dev0",
|
28 |
"vision_config": {
|
29 |
"attention_dropout": 0.1,
|
30 |
"dropout": 0.1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2208c870ffdd0d1e0771b76aa54fee8c86f0900a637c635aa9e2865334eda78c
|
3 |
size 90104
|
preprocessor_config.json
CHANGED
@@ -1,4 +1,21 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"crop_size": {
|
3 |
"height": 30,
|
4 |
"width": 30
|
|
|
1 |
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
"crop_size": {
|
20 |
"height": 30,
|
21 |
"width": 30
|
tokenizer.json
CHANGED
@@ -254,137 +254,137 @@
|
|
254 |
"Ł": 164,
|
255 |
"ł": 165,
|
256 |
"Ń": 166,
|
257 |
-
"
|
258 |
-
"
|
259 |
-
"
|
260 |
-
"
|
261 |
-
"
|
262 |
-
"
|
263 |
-
"
|
264 |
-
"
|
265 |
-
"
|
266 |
-
"
|
267 |
-
"
|
268 |
-
"
|
269 |
-
"
|
270 |
-
"
|
271 |
-
"
|
272 |
-
"
|
273 |
-
"
|
274 |
-
"
|
275 |
-
"
|
276 |
-
"
|
277 |
-
"
|
278 |
-
"
|
279 |
-
"w
|
280 |
-
"
|
281 |
-
"
|
282 |
-
"
|
283 |
-
"
|
284 |
-
"
|
285 |
-
"
|
286 |
-
"
|
287 |
-
"
|
288 |
-
"
|
289 |
-
"
|
290 |
-
"
|
291 |
-
"
|
292 |
-
"
|
293 |
-
"
|
294 |
-
"
|
295 |
-
"
|
296 |
-
"
|
297 |
"¢</w>": 207,
|
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 |
"'</w>": 261,
|
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 |
"th": 298,
|
389 |
"the</w>": 299,
|
390 |
"in": 300,
|
|
|
254 |
"Ł": 164,
|
255 |
"ł": 165,
|
256 |
"Ń": 166,
|
257 |
+
"t</w>": 167,
|
258 |
+
"e</w>": 168,
|
259 |
+
"d</w>": 169,
|
260 |
+
"u</w>": 170,
|
261 |
+
"g</w>": 171,
|
262 |
+
"l</w>": 172,
|
263 |
+
"n</w>": 173,
|
264 |
+
"r</w>": 174,
|
265 |
+
"i</w>": 175,
|
266 |
+
"m</w>": 176,
|
267 |
+
"a</w>": 177,
|
268 |
+
"y</w>": 178,
|
269 |
+
"s</w>": 179,
|
270 |
+
"w</w>": 180,
|
271 |
+
"¦</w>": 181,
|
272 |
+
"f</w>": 182,
|
273 |
+
"ĩ</w>": 183,
|
274 |
+
"b</w>": 184,
|
275 |
+
"p</w>": 185,
|
276 |
+
"c</w>": 186,
|
277 |
+
"z</w>": 187,
|
278 |
+
"h</w>": 188,
|
279 |
+
"Ī</w>": 189,
|
280 |
+
"o</w>": 190,
|
281 |
+
"Ľ</w>": 191,
|
282 |
+
"k</w>": 192,
|
283 |
+
"v</w>": 193,
|
284 |
+
"²</w>": 194,
|
285 |
+
"®</w>": 195,
|
286 |
+
"ľ</w>": 196,
|
287 |
+
"¿</w>": 197,
|
288 |
+
"x</w>": 198,
|
289 |
+
"º</w>": 199,
|
290 |
+
"3</w>": 200,
|
291 |
+
"ķ</w>": 201,
|
292 |
+
"j</w>": 202,
|
293 |
+
"Ķ</w>": 203,
|
294 |
+
"´</w>": 204,
|
295 |
+
"IJ</w>": 205,
|
296 |
+
"¹</w>": 206,
|
297 |
"¢</w>": 207,
|
298 |
+
"-</w>": 208,
|
299 |
+
"Ĥ</w>": 209,
|
300 |
+
"¼</w>": 210,
|
301 |
+
"·</w>": 211,
|
302 |
+
"½</w>": 212,
|
303 |
+
"ģ</w>": 213,
|
304 |
+
"ĺ</w>": 214,
|
305 |
+
"Ŀ</w>": 215,
|
306 |
+
"¡</w>": 216,
|
307 |
+
"į</w>": 217,
|
308 |
+
"©</w>": 218,
|
309 |
+
"Ĺ</w>": 219,
|
310 |
+
"%</w>": 220,
|
311 |
+
"Ń</w>": 221,
|
312 |
+
"ĸ</w>": 222,
|
313 |
+
"«</w>": 223,
|
314 |
+
"±</w>": 224,
|
315 |
+
"¯</w>": 225,
|
316 |
+
"ļ</w>": 226,
|
317 |
+
"q</w>": 227,
|
318 |
+
"»</w>": 228,
|
319 |
+
"ī</w>": 229,
|
320 |
+
"2</w>": 230,
|
321 |
+
"ij</w>": 231,
|
322 |
+
"³</w>": 232,
|
323 |
+
"¸</w>": 233,
|
324 |
+
"¨</w>": 234,
|
325 |
+
"ª</w>": 235,
|
326 |
+
"Ł</w>": 236,
|
327 |
+
"ł</w>": 237,
|
328 |
+
"^</w>": 238,
|
329 |
+
"Ĩ</w>": 239,
|
330 |
+
"£</w>": 240,
|
331 |
+
"5</w>": 241,
|
332 |
+
"ĥ</w>": 242,
|
333 |
+
"Ļ</w>": 243,
|
334 |
+
"¤</w>": 244,
|
335 |
+
"¾</w>": 245,
|
336 |
+
"Ĵ</w>": 246,
|
337 |
+
"Ģ</w>": 247,
|
338 |
+
"@</w>": 248,
|
339 |
+
"¬</w>": 249,
|
340 |
+
"¶</w>": 250,
|
341 |
+
"°</w>": 251,
|
342 |
+
"Ħ</w>": 252,
|
343 |
+
"<</w>": 253,
|
344 |
+
"ħ</w>": 254,
|
345 |
+
".</w>": 255,
|
346 |
+
"1</w>": 256,
|
347 |
+
"ĵ</w>": 257,
|
348 |
+
"µ</w>": 258,
|
349 |
+
"`</w>": 259,
|
350 |
+
"$</w>": 260,
|
351 |
"'</w>": 261,
|
352 |
+
"§</w>": 262,
|
353 |
+
"Ĭ</w>": 263,
|
354 |
+
"|</w>": 264,
|
355 |
+
"ŀ</w>": 265,
|
356 |
+
"Į</w>": 266,
|
357 |
+
":</w>": 267,
|
358 |
+
"İ</w>": 268,
|
359 |
+
"]</w>": 269,
|
360 |
+
"=</w>": 270,
|
361 |
+
"6</w>": 271,
|
362 |
+
"9</w>": 272,
|
363 |
+
"¥</w>": 273,
|
364 |
+
"ĭ</w>": 274,
|
365 |
+
"ı</w>": 275,
|
366 |
+
"></w>": 276,
|
367 |
+
"7</w>": 277,
|
368 |
+
";</w>": 278,
|
369 |
+
"}</w>": 279,
|
370 |
+
"~</w>": 280,
|
371 |
+
"_</w>": 281,
|
372 |
+
"(</w>": 282,
|
373 |
+
"0</w>": 283,
|
374 |
+
"+</w>": 284,
|
375 |
+
"!</w>": 285,
|
376 |
+
"#</w>": 286,
|
377 |
+
"?</w>": 287,
|
378 |
+
"\"</w>": 288,
|
379 |
+
")</w>": 289,
|
380 |
+
"&</w>": 290,
|
381 |
+
"*</w>": 291,
|
382 |
+
",</w>": 292,
|
383 |
+
"4</w>": 293,
|
384 |
+
"\\</w>": 294,
|
385 |
+
"8</w>": 295,
|
386 |
+
"[</w>": 296,
|
387 |
+
"/</w>": 297,
|
388 |
"th": 298,
|
389 |
"the</w>": 299,
|
390 |
"in": 300,
|
vocab.json
CHANGED
@@ -1,91 +1,91 @@
|
|
1 |
{
|
2 |
"!": 2,
|
3 |
-
"!</w>":
|
4 |
"\"": 3,
|
5 |
-
"\"</w>":
|
6 |
"#": 4,
|
7 |
-
"#</w>":
|
8 |
"$": 5,
|
9 |
-
"$</w>":
|
10 |
"%": 6,
|
11 |
-
"%</w>":
|
12 |
"&": 7,
|
13 |
-
"&</w>":
|
14 |
"'": 8,
|
15 |
"'</w>": 261,
|
16 |
"'s</w>": 363,
|
17 |
"(": 9,
|
18 |
-
"(</w>":
|
19 |
")": 10,
|
20 |
-
")</w>":
|
21 |
"*": 11,
|
22 |
-
"*</w>":
|
23 |
"+": 12,
|
24 |
-
"+</w>":
|
25 |
",": 13,
|
26 |
-
",</w>":
|
27 |
",@</w>": 622,
|
28 |
"-": 14,
|
29 |
-
"-</w>":
|
30 |
"-@</w>": 353,
|
31 |
".": 15,
|
32 |
-
".</w>":
|
33 |
".@</w>": 569,
|
34 |
"/": 16,
|
35 |
-
"/</w>":
|
36 |
"0": 17,
|
37 |
-
"0</w>":
|
38 |
"1": 18,
|
39 |
-
"1</w>":
|
40 |
"2": 19,
|
41 |
-
"2</w>":
|
42 |
"3": 20,
|
43 |
-
"3</w>":
|
44 |
"4": 21,
|
45 |
-
"4</w>":
|
46 |
"5": 22,
|
47 |
-
"5</w>":
|
48 |
"6": 23,
|
49 |
-
"6</w>":
|
50 |
"7": 24,
|
51 |
-
"7</w>":
|
52 |
"8": 25,
|
53 |
-
"8</w>":
|
54 |
"9": 26,
|
55 |
-
"9</w>":
|
56 |
":": 27,
|
57 |
-
":</w>":
|
58 |
";": 28,
|
59 |
-
";</w>":
|
60 |
"<": 29,
|
61 |
-
"<</w>":
|
62 |
"<|endoftext|>": 1,
|
63 |
"<|startoftext|>": 0,
|
64 |
"=": 30,
|
65 |
-
"=</w>":
|
66 |
">": 31,
|
67 |
-
"></w>":
|
68 |
"?": 32,
|
69 |
-
"?</w>":
|
70 |
"@": 33,
|
71 |
"@,@</w>": 623,
|
72 |
"@-@</w>": 354,
|
73 |
"@.@</w>": 570,
|
74 |
-
"@</w>":
|
75 |
"[": 34,
|
76 |
-
"[</w>":
|
77 |
"\\": 35,
|
78 |
-
"\\</w>":
|
79 |
"]": 36,
|
80 |
-
"]</w>":
|
81 |
"^": 37,
|
82 |
-
"^</w>":
|
83 |
"_": 38,
|
84 |
-
"_</w>":
|
85 |
"`": 39,
|
86 |
-
"`</w>":
|
87 |
"a": 40,
|
88 |
-
"a</w>":
|
89 |
"ab": 408,
|
90 |
"able</w>": 675,
|
91 |
"about</w>": 721,
|
@@ -158,7 +158,7 @@
|
|
158 |
"au": 448,
|
159 |
"ause</w>": 997,
|
160 |
"b": 41,
|
161 |
-
"b</w>":
|
162 |
"ba": 687,
|
163 |
"back</w>": 992,
|
164 |
"bar": 821,
|
@@ -194,7 +194,7 @@
|
|
194 |
"but</w>": 499,
|
195 |
"by</w>": 369,
|
196 |
"c": 42,
|
197 |
-
"c</w>":
|
198 |
"ca": 394,
|
199 |
"cal": 820,
|
200 |
"called</w>": 1014,
|
@@ -243,7 +243,7 @@
|
|
243 |
"cul": 881,
|
244 |
"cur": 990,
|
245 |
"d": 43,
|
246 |
-
"d</w>":
|
247 |
"da": 497,
|
248 |
"day</w>": 755,
|
249 |
"de": 352,
|
@@ -275,7 +275,7 @@
|
|
275 |
"during</w>": 616,
|
276 |
"dy</w>": 727,
|
277 |
"e": 44,
|
278 |
-
"e</w>":
|
279 |
"ea": 344,
|
280 |
"eam</w>": 1006,
|
281 |
"ear": 445,
|
@@ -326,7 +326,7 @@
|
|
326 |
"ever</w>": 754,
|
327 |
"ex": 417,
|
328 |
"f": 45,
|
329 |
-
"f</w>":
|
330 |
"fa": 630,
|
331 |
"fac": 893,
|
332 |
"fe": 484,
|
@@ -355,7 +355,7 @@
|
|
355 |
"ft</w>": 707,
|
356 |
"fu": 665,
|
357 |
"g": 46,
|
358 |
-
"g</w>":
|
359 |
"ga": 631,
|
360 |
"game</w>": 697,
|
361 |
"gan</w>": 835,
|
@@ -378,7 +378,7 @@
|
|
378 |
"gs</w>": 975,
|
379 |
"gu": 426,
|
380 |
"h": 47,
|
381 |
-
"h</w>":
|
382 |
"ha": 367,
|
383 |
"had</w>": 459,
|
384 |
"har": 971,
|
@@ -400,7 +400,7 @@
|
|
400 |
"however</w>": 867,
|
401 |
"hu": 993,
|
402 |
"i": 48,
|
403 |
-
"i</w>":
|
404 |
"ic": 409,
|
405 |
"ic</w>": 783,
|
406 |
"ical</w>": 713,
|
@@ -438,12 +438,12 @@
|
|
438 |
"its</w>": 480,
|
439 |
"ity</w>": 443,
|
440 |
"j": 49,
|
441 |
-
"j</w>":
|
442 |
"jo": 585,
|
443 |
"joh": 941,
|
444 |
"ju": 619,
|
445 |
"k": 50,
|
446 |
-
"k</w>":
|
447 |
"ke": 661,
|
448 |
"ke</w>": 505,
|
449 |
"ked</w>": 653,
|
@@ -452,7 +452,7 @@
|
|
452 |
"known</w>": 879,
|
453 |
"ks</w>": 559,
|
454 |
"l": 51,
|
455 |
-
"l</w>":
|
456 |
"la": 348,
|
457 |
"lan": 606,
|
458 |
"land</w>": 561,
|
@@ -481,7 +481,7 @@
|
|
481 |
"lu": 432,
|
482 |
"ly</w>": 342,
|
483 |
"m": 52,
|
484 |
-
"m</w>":
|
485 |
"ma": 365,
|
486 |
"made</w>": 794,
|
487 |
"man": 444,
|
@@ -508,7 +508,7 @@
|
|
508 |
"musi": 808,
|
509 |
"music</w>": 961,
|
510 |
"n": 53,
|
511 |
-
"n</w>":
|
512 |
"na": 517,
|
513 |
"nam": 810,
|
514 |
"national</w>": 849,
|
@@ -527,7 +527,7 @@
|
|
527 |
"num": 763,
|
528 |
"number</w>": 924,
|
529 |
"o": 54,
|
530 |
-
"o</w>":
|
531 |
"ob": 909,
|
532 |
"oc": 511,
|
533 |
"od</w>": 825,
|
@@ -571,7 +571,7 @@
|
|
571 |
"ow": 416,
|
572 |
"own</w>": 617,
|
573 |
"p": 55,
|
574 |
-
"p</w>":
|
575 |
"pa": 593,
|
576 |
"par": 427,
|
577 |
"part</w>": 892,
|
@@ -604,10 +604,10 @@
|
|
604 |
"pu": 485,
|
605 |
"publi": 728,
|
606 |
"q": 56,
|
607 |
-
"q</w>":
|
608 |
"qu": 431,
|
609 |
"r": 57,
|
610 |
-
"r</w>":
|
611 |
"ra": 355,
|
612 |
"ran": 523,
|
613 |
"re": 304,
|
@@ -629,7 +629,7 @@
|
|
629 |
"ru": 419,
|
630 |
"ry</w>": 885,
|
631 |
"s": 58,
|
632 |
-
"s</w>":
|
633 |
"sa": 510,
|
634 |
"sc": 414,
|
635 |
"sch": 775,
|
@@ -705,7 +705,7 @@
|
|
705 |
"sur": 642,
|
706 |
"sy": 673,
|
707 |
"t": 59,
|
708 |
-
"t</w>":
|
709 |
"ta": 438,
|
710 |
"tain</w>": 1010,
|
711 |
"te": 544,
|
@@ -775,7 +775,7 @@
|
|
775 |
"two</w>": 545,
|
776 |
"ty</w>": 584,
|
777 |
"u": 60,
|
778 |
-
"u</w>":
|
779 |
"ul": 461,
|
780 |
"um": 500,
|
781 |
"um</w>": 743,
|
@@ -793,7 +793,7 @@
|
|
793 |
"use</w>": 991,
|
794 |
"used</w>": 701,
|
795 |
"v": 61,
|
796 |
-
"v</w>":
|
797 |
"ve": 910,
|
798 |
"ve</w>": 371,
|
799 |
"ved</w>": 503,
|
@@ -809,7 +809,7 @@
|
|
809 |
"vision</w>": 873,
|
810 |
"vo": 852,
|
811 |
"w": 62,
|
812 |
-
"w</w>":
|
813 |
"wa": 464,
|
814 |
"war": 768,
|
815 |
"war</w>": 866,
|
@@ -840,9 +840,9 @@
|
|
840 |
"writ": 722,
|
841 |
"ws</w>": 953,
|
842 |
"x": 63,
|
843 |
-
"x</w>":
|
844 |
"y": 64,
|
845 |
-
"y</w>":
|
846 |
"year</w>": 789,
|
847 |
"years</w>": 845,
|
848 |
"ying</w>": 868,
|
@@ -850,74 +850,74 @@
|
|
850 |
"yp": 870,
|
851 |
"ys</w>": 711,
|
852 |
"z": 65,
|
853 |
-
"z</w>":
|
854 |
"zed</w>": 973,
|
855 |
"|": 66,
|
856 |
-
"|</w>":
|
857 |
"}": 67,
|
858 |
-
"}</w>":
|
859 |
"~": 68,
|
860 |
-
"~</w>":
|
861 |
"¡": 69,
|
862 |
-
"¡</w>":
|
863 |
"¢": 70,
|
864 |
"¢</w>": 207,
|
865 |
"£": 71,
|
866 |
-
"£</w>":
|
867 |
"¤": 72,
|
868 |
-
"¤</w>":
|
869 |
"¥": 73,
|
870 |
-
"¥</w>":
|
871 |
"¦": 74,
|
872 |
-
"¦</w>":
|
873 |
"§": 75,
|
874 |
-
"§</w>":
|
875 |
"¨": 76,
|
876 |
-
"¨</w>":
|
877 |
"©": 77,
|
878 |
-
"©</w>":
|
879 |
"ª": 78,
|
880 |
-
"ª</w>":
|
881 |
"«": 79,
|
882 |
-
"«</w>":
|
883 |
"¬": 80,
|
884 |
-
"¬</w>":
|
885 |
"®": 81,
|
886 |
-
"®</w>":
|
887 |
"¯": 82,
|
888 |
-
"¯</w>":
|
889 |
"°": 83,
|
890 |
-
"°</w>":
|
891 |
"±": 84,
|
892 |
-
"±</w>":
|
893 |
"²": 85,
|
894 |
-
"²</w>":
|
895 |
"³": 86,
|
896 |
-
"³</w>":
|
897 |
"´": 87,
|
898 |
-
"´</w>":
|
899 |
"µ": 88,
|
900 |
-
"µ</w>":
|
901 |
"¶": 89,
|
902 |
-
"¶</w>":
|
903 |
"·": 90,
|
904 |
-
"·</w>":
|
905 |
"¸": 91,
|
906 |
-
"¸</w>":
|
907 |
"¹": 92,
|
908 |
-
"¹</w>":
|
909 |
"º": 93,
|
910 |
-
"º</w>":
|
911 |
"»": 94,
|
912 |
-
"»</w>":
|
913 |
"¼": 95,
|
914 |
-
"¼</w>":
|
915 |
"½": 96,
|
916 |
-
"½</w>":
|
917 |
"¾": 97,
|
918 |
-
"¾</w>":
|
919 |
"¿": 98,
|
920 |
-
"¿</w>":
|
921 |
"Â": 99,
|
922 |
"Ã": 100,
|
923 |
"Ä": 101,
|
@@ -956,71 +956,71 @@
|
|
956 |
"ì": 131,
|
957 |
"ï": 132,
|
958 |
"Ģ": 133,
|
959 |
-
"Ģ</w>":
|
960 |
"ģ": 134,
|
961 |
-
"ģ</w>":
|
962 |
"Ĥ": 135,
|
963 |
-
"Ĥ</w>":
|
964 |
"ĥ": 136,
|
965 |
-
"ĥ</w>":
|
966 |
"Ħ": 137,
|
967 |
-
"Ħ</w>":
|
968 |
"ħ": 138,
|
969 |
-
"ħ</w>":
|
970 |
"Ĩ": 139,
|
971 |
-
"Ĩ</w>":
|
972 |
"ĩ": 140,
|
973 |
-
"ĩ</w>":
|
974 |
"Ī": 141,
|
975 |
-
"Ī</w>":
|
976 |
"ī": 142,
|
977 |
-
"ī</w>":
|
978 |
"Ĭ": 143,
|
979 |
-
"Ĭ</w>":
|
980 |
"ĭ": 144,
|
981 |
-
"ĭ</w>":
|
982 |
"Į": 145,
|
983 |
-
"Į</w>":
|
984 |
"į": 146,
|
985 |
-
"į</w>":
|
986 |
"İ": 147,
|
987 |
-
"İ</w>":
|
988 |
"ı": 148,
|
989 |
-
"ı</w>":
|
990 |
"IJ": 149,
|
991 |
-
"IJ</w>":
|
992 |
"ij": 150,
|
993 |
-
"ij</w>":
|
994 |
"Ĵ": 151,
|
995 |
-
"Ĵ</w>":
|
996 |
"ĵ": 152,
|
997 |
-
"ĵ</w>":
|
998 |
"Ķ": 153,
|
999 |
-
"Ķ</w>":
|
1000 |
"ķ": 154,
|
1001 |
-
"ķ</w>":
|
1002 |
"ĸ": 155,
|
1003 |
-
"ĸ</w>":
|
1004 |
"Ĺ": 156,
|
1005 |
-
"Ĺ</w>":
|
1006 |
"ĺ": 157,
|
1007 |
-
"ĺ</w>":
|
1008 |
"Ļ": 158,
|
1009 |
-
"Ļ</w>":
|
1010 |
"ļ": 159,
|
1011 |
-
"ļ</w>":
|
1012 |
"Ľ": 160,
|
1013 |
-
"Ľ</w>":
|
1014 |
"ľ": 161,
|
1015 |
-
"ľ</w>":
|
1016 |
"Ŀ": 162,
|
1017 |
-
"Ŀ</w>":
|
1018 |
"ŀ": 163,
|
1019 |
-
"ŀ</w>":
|
1020 |
"Ł": 164,
|
1021 |
-
"Ł</w>":
|
1022 |
"ł": 165,
|
1023 |
-
"ł</w>":
|
1024 |
"Ń": 166,
|
1025 |
-
"Ń</w>":
|
1026 |
}
|
|
|
1 |
{
|
2 |
"!": 2,
|
3 |
+
"!</w>": 285,
|
4 |
"\"": 3,
|
5 |
+
"\"</w>": 288,
|
6 |
"#": 4,
|
7 |
+
"#</w>": 286,
|
8 |
"$": 5,
|
9 |
+
"$</w>": 260,
|
10 |
"%": 6,
|
11 |
+
"%</w>": 220,
|
12 |
"&": 7,
|
13 |
+
"&</w>": 290,
|
14 |
"'": 8,
|
15 |
"'</w>": 261,
|
16 |
"'s</w>": 363,
|
17 |
"(": 9,
|
18 |
+
"(</w>": 282,
|
19 |
")": 10,
|
20 |
+
")</w>": 289,
|
21 |
"*": 11,
|
22 |
+
"*</w>": 291,
|
23 |
"+": 12,
|
24 |
+
"+</w>": 284,
|
25 |
",": 13,
|
26 |
+
",</w>": 292,
|
27 |
",@</w>": 622,
|
28 |
"-": 14,
|
29 |
+
"-</w>": 208,
|
30 |
"-@</w>": 353,
|
31 |
".": 15,
|
32 |
+
".</w>": 255,
|
33 |
".@</w>": 569,
|
34 |
"/": 16,
|
35 |
+
"/</w>": 297,
|
36 |
"0": 17,
|
37 |
+
"0</w>": 283,
|
38 |
"1": 18,
|
39 |
+
"1</w>": 256,
|
40 |
"2": 19,
|
41 |
+
"2</w>": 230,
|
42 |
"3": 20,
|
43 |
+
"3</w>": 200,
|
44 |
"4": 21,
|
45 |
+
"4</w>": 293,
|
46 |
"5": 22,
|
47 |
+
"5</w>": 241,
|
48 |
"6": 23,
|
49 |
+
"6</w>": 271,
|
50 |
"7": 24,
|
51 |
+
"7</w>": 277,
|
52 |
"8": 25,
|
53 |
+
"8</w>": 295,
|
54 |
"9": 26,
|
55 |
+
"9</w>": 272,
|
56 |
":": 27,
|
57 |
+
":</w>": 267,
|
58 |
";": 28,
|
59 |
+
";</w>": 278,
|
60 |
"<": 29,
|
61 |
+
"<</w>": 253,
|
62 |
"<|endoftext|>": 1,
|
63 |
"<|startoftext|>": 0,
|
64 |
"=": 30,
|
65 |
+
"=</w>": 270,
|
66 |
">": 31,
|
67 |
+
"></w>": 276,
|
68 |
"?": 32,
|
69 |
+
"?</w>": 287,
|
70 |
"@": 33,
|
71 |
"@,@</w>": 623,
|
72 |
"@-@</w>": 354,
|
73 |
"@.@</w>": 570,
|
74 |
+
"@</w>": 248,
|
75 |
"[": 34,
|
76 |
+
"[</w>": 296,
|
77 |
"\\": 35,
|
78 |
+
"\\</w>": 294,
|
79 |
"]": 36,
|
80 |
+
"]</w>": 269,
|
81 |
"^": 37,
|
82 |
+
"^</w>": 238,
|
83 |
"_": 38,
|
84 |
+
"_</w>": 281,
|
85 |
"`": 39,
|
86 |
+
"`</w>": 259,
|
87 |
"a": 40,
|
88 |
+
"a</w>": 177,
|
89 |
"ab": 408,
|
90 |
"able</w>": 675,
|
91 |
"about</w>": 721,
|
|
|
158 |
"au": 448,
|
159 |
"ause</w>": 997,
|
160 |
"b": 41,
|
161 |
+
"b</w>": 184,
|
162 |
"ba": 687,
|
163 |
"back</w>": 992,
|
164 |
"bar": 821,
|
|
|
194 |
"but</w>": 499,
|
195 |
"by</w>": 369,
|
196 |
"c": 42,
|
197 |
+
"c</w>": 186,
|
198 |
"ca": 394,
|
199 |
"cal": 820,
|
200 |
"called</w>": 1014,
|
|
|
243 |
"cul": 881,
|
244 |
"cur": 990,
|
245 |
"d": 43,
|
246 |
+
"d</w>": 169,
|
247 |
"da": 497,
|
248 |
"day</w>": 755,
|
249 |
"de": 352,
|
|
|
275 |
"during</w>": 616,
|
276 |
"dy</w>": 727,
|
277 |
"e": 44,
|
278 |
+
"e</w>": 168,
|
279 |
"ea": 344,
|
280 |
"eam</w>": 1006,
|
281 |
"ear": 445,
|
|
|
326 |
"ever</w>": 754,
|
327 |
"ex": 417,
|
328 |
"f": 45,
|
329 |
+
"f</w>": 182,
|
330 |
"fa": 630,
|
331 |
"fac": 893,
|
332 |
"fe": 484,
|
|
|
355 |
"ft</w>": 707,
|
356 |
"fu": 665,
|
357 |
"g": 46,
|
358 |
+
"g</w>": 171,
|
359 |
"ga": 631,
|
360 |
"game</w>": 697,
|
361 |
"gan</w>": 835,
|
|
|
378 |
"gs</w>": 975,
|
379 |
"gu": 426,
|
380 |
"h": 47,
|
381 |
+
"h</w>": 188,
|
382 |
"ha": 367,
|
383 |
"had</w>": 459,
|
384 |
"har": 971,
|
|
|
400 |
"however</w>": 867,
|
401 |
"hu": 993,
|
402 |
"i": 48,
|
403 |
+
"i</w>": 175,
|
404 |
"ic": 409,
|
405 |
"ic</w>": 783,
|
406 |
"ical</w>": 713,
|
|
|
438 |
"its</w>": 480,
|
439 |
"ity</w>": 443,
|
440 |
"j": 49,
|
441 |
+
"j</w>": 202,
|
442 |
"jo": 585,
|
443 |
"joh": 941,
|
444 |
"ju": 619,
|
445 |
"k": 50,
|
446 |
+
"k</w>": 192,
|
447 |
"ke": 661,
|
448 |
"ke</w>": 505,
|
449 |
"ked</w>": 653,
|
|
|
452 |
"known</w>": 879,
|
453 |
"ks</w>": 559,
|
454 |
"l": 51,
|
455 |
+
"l</w>": 172,
|
456 |
"la": 348,
|
457 |
"lan": 606,
|
458 |
"land</w>": 561,
|
|
|
481 |
"lu": 432,
|
482 |
"ly</w>": 342,
|
483 |
"m": 52,
|
484 |
+
"m</w>": 176,
|
485 |
"ma": 365,
|
486 |
"made</w>": 794,
|
487 |
"man": 444,
|
|
|
508 |
"musi": 808,
|
509 |
"music</w>": 961,
|
510 |
"n": 53,
|
511 |
+
"n</w>": 173,
|
512 |
"na": 517,
|
513 |
"nam": 810,
|
514 |
"national</w>": 849,
|
|
|
527 |
"num": 763,
|
528 |
"number</w>": 924,
|
529 |
"o": 54,
|
530 |
+
"o</w>": 190,
|
531 |
"ob": 909,
|
532 |
"oc": 511,
|
533 |
"od</w>": 825,
|
|
|
571 |
"ow": 416,
|
572 |
"own</w>": 617,
|
573 |
"p": 55,
|
574 |
+
"p</w>": 185,
|
575 |
"pa": 593,
|
576 |
"par": 427,
|
577 |
"part</w>": 892,
|
|
|
604 |
"pu": 485,
|
605 |
"publi": 728,
|
606 |
"q": 56,
|
607 |
+
"q</w>": 227,
|
608 |
"qu": 431,
|
609 |
"r": 57,
|
610 |
+
"r</w>": 174,
|
611 |
"ra": 355,
|
612 |
"ran": 523,
|
613 |
"re": 304,
|
|
|
629 |
"ru": 419,
|
630 |
"ry</w>": 885,
|
631 |
"s": 58,
|
632 |
+
"s</w>": 179,
|
633 |
"sa": 510,
|
634 |
"sc": 414,
|
635 |
"sch": 775,
|
|
|
705 |
"sur": 642,
|
706 |
"sy": 673,
|
707 |
"t": 59,
|
708 |
+
"t</w>": 167,
|
709 |
"ta": 438,
|
710 |
"tain</w>": 1010,
|
711 |
"te": 544,
|
|
|
775 |
"two</w>": 545,
|
776 |
"ty</w>": 584,
|
777 |
"u": 60,
|
778 |
+
"u</w>": 170,
|
779 |
"ul": 461,
|
780 |
"um": 500,
|
781 |
"um</w>": 743,
|
|
|
793 |
"use</w>": 991,
|
794 |
"used</w>": 701,
|
795 |
"v": 61,
|
796 |
+
"v</w>": 193,
|
797 |
"ve": 910,
|
798 |
"ve</w>": 371,
|
799 |
"ved</w>": 503,
|
|
|
809 |
"vision</w>": 873,
|
810 |
"vo": 852,
|
811 |
"w": 62,
|
812 |
+
"w</w>": 180,
|
813 |
"wa": 464,
|
814 |
"war": 768,
|
815 |
"war</w>": 866,
|
|
|
840 |
"writ": 722,
|
841 |
"ws</w>": 953,
|
842 |
"x": 63,
|
843 |
+
"x</w>": 198,
|
844 |
"y": 64,
|
845 |
+
"y</w>": 178,
|
846 |
"year</w>": 789,
|
847 |
"years</w>": 845,
|
848 |
"ying</w>": 868,
|
|
|
850 |
"yp": 870,
|
851 |
"ys</w>": 711,
|
852 |
"z": 65,
|
853 |
+
"z</w>": 187,
|
854 |
"zed</w>": 973,
|
855 |
"|": 66,
|
856 |
+
"|</w>": 264,
|
857 |
"}": 67,
|
858 |
+
"}</w>": 279,
|
859 |
"~": 68,
|
860 |
+
"~</w>": 280,
|
861 |
"¡": 69,
|
862 |
+
"¡</w>": 216,
|
863 |
"¢": 70,
|
864 |
"¢</w>": 207,
|
865 |
"£": 71,
|
866 |
+
"£</w>": 240,
|
867 |
"¤": 72,
|
868 |
+
"¤</w>": 244,
|
869 |
"¥": 73,
|
870 |
+
"¥</w>": 273,
|
871 |
"¦": 74,
|
872 |
+
"¦</w>": 181,
|
873 |
"§": 75,
|
874 |
+
"§</w>": 262,
|
875 |
"¨": 76,
|
876 |
+
"¨</w>": 234,
|
877 |
"©": 77,
|
878 |
+
"©</w>": 218,
|
879 |
"ª": 78,
|
880 |
+
"ª</w>": 235,
|
881 |
"«": 79,
|
882 |
+
"«</w>": 223,
|
883 |
"¬": 80,
|
884 |
+
"¬</w>": 249,
|
885 |
"®": 81,
|
886 |
+
"®</w>": 195,
|
887 |
"¯": 82,
|
888 |
+
"¯</w>": 225,
|
889 |
"°": 83,
|
890 |
+
"°</w>": 251,
|
891 |
"±": 84,
|
892 |
+
"±</w>": 224,
|
893 |
"²": 85,
|
894 |
+
"²</w>": 194,
|
895 |
"³": 86,
|
896 |
+
"³</w>": 232,
|
897 |
"´": 87,
|
898 |
+
"´</w>": 204,
|
899 |
"µ": 88,
|
900 |
+
"µ</w>": 258,
|
901 |
"¶": 89,
|
902 |
+
"¶</w>": 250,
|
903 |
"·": 90,
|
904 |
+
"·</w>": 211,
|
905 |
"¸": 91,
|
906 |
+
"¸</w>": 233,
|
907 |
"¹": 92,
|
908 |
+
"¹</w>": 206,
|
909 |
"º": 93,
|
910 |
+
"º</w>": 199,
|
911 |
"»": 94,
|
912 |
+
"»</w>": 228,
|
913 |
"¼": 95,
|
914 |
+
"¼</w>": 210,
|
915 |
"½": 96,
|
916 |
+
"½</w>": 212,
|
917 |
"¾": 97,
|
918 |
+
"¾</w>": 245,
|
919 |
"¿": 98,
|
920 |
+
"¿</w>": 197,
|
921 |
"Â": 99,
|
922 |
"Ã": 100,
|
923 |
"Ä": 101,
|
|
|
956 |
"ì": 131,
|
957 |
"ï": 132,
|
958 |
"Ģ": 133,
|
959 |
+
"Ģ</w>": 247,
|
960 |
"ģ": 134,
|
961 |
+
"ģ</w>": 213,
|
962 |
"Ĥ": 135,
|
963 |
+
"Ĥ</w>": 209,
|
964 |
"ĥ": 136,
|
965 |
+
"ĥ</w>": 242,
|
966 |
"Ħ": 137,
|
967 |
+
"Ħ</w>": 252,
|
968 |
"ħ": 138,
|
969 |
+
"ħ</w>": 254,
|
970 |
"Ĩ": 139,
|
971 |
+
"Ĩ</w>": 239,
|
972 |
"ĩ": 140,
|
973 |
+
"ĩ</w>": 183,
|
974 |
"Ī": 141,
|
975 |
+
"Ī</w>": 189,
|
976 |
"ī": 142,
|
977 |
+
"ī</w>": 229,
|
978 |
"Ĭ": 143,
|
979 |
+
"Ĭ</w>": 263,
|
980 |
"ĭ": 144,
|
981 |
+
"ĭ</w>": 274,
|
982 |
"Į": 145,
|
983 |
+
"Į</w>": 266,
|
984 |
"į": 146,
|
985 |
+
"į</w>": 217,
|
986 |
"İ": 147,
|
987 |
+
"İ</w>": 268,
|
988 |
"ı": 148,
|
989 |
+
"ı</w>": 275,
|
990 |
"IJ": 149,
|
991 |
+
"IJ</w>": 205,
|
992 |
"ij": 150,
|
993 |
+
"ij</w>": 231,
|
994 |
"Ĵ": 151,
|
995 |
+
"Ĵ</w>": 246,
|
996 |
"ĵ": 152,
|
997 |
+
"ĵ</w>": 257,
|
998 |
"Ķ": 153,
|
999 |
+
"Ķ</w>": 203,
|
1000 |
"ķ": 154,
|
1001 |
+
"ķ</w>": 201,
|
1002 |
"ĸ": 155,
|
1003 |
+
"ĸ</w>": 222,
|
1004 |
"Ĺ": 156,
|
1005 |
+
"Ĺ</w>": 219,
|
1006 |
"ĺ": 157,
|
1007 |
+
"ĺ</w>": 214,
|
1008 |
"Ļ": 158,
|
1009 |
+
"Ļ</w>": 243,
|
1010 |
"ļ": 159,
|
1011 |
+
"ļ</w>": 226,
|
1012 |
"Ľ": 160,
|
1013 |
+
"Ľ</w>": 191,
|
1014 |
"ľ": 161,
|
1015 |
+
"ľ</w>": 196,
|
1016 |
"Ŀ": 162,
|
1017 |
+
"Ŀ</w>": 215,
|
1018 |
"ŀ": 163,
|
1019 |
+
"ŀ</w>": 265,
|
1020 |
"Ł": 164,
|
1021 |
+
"Ł</w>": 236,
|
1022 |
"ł": 165,
|
1023 |
+
"ł</w>": 237,
|
1024 |
"Ń": 166,
|
1025 |
+
"Ń</w>": 221
|
1026 |
}
|