Update tiny models for CLIPForImageClassification
Browse files- config.json +1 -1
- model.safetensors +1 -1
- preprocessor_config.json +17 -0
- tokenizer.json +130 -130
- vocab.json +130 -130
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:cf19deb171ab092df3897e7b6fc2b5e4601df07a7c3ff3b88065092709288cc8
|
| 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 |
-
"
|
| 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 |
"¹</w>": 226,
|
| 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 |
"th": 298,
|
| 389 |
"the</w>": 299,
|
| 390 |
"in": 300,
|
|
|
|
| 254 |
"Ł": 164,
|
| 255 |
"ł": 165,
|
| 256 |
"Ń": 166,
|
| 257 |
+
"s</w>": 167,
|
| 258 |
+
"d</w>": 168,
|
| 259 |
+
"e</w>": 169,
|
| 260 |
+
"n</w>": 170,
|
| 261 |
+
"ª</w>": 171,
|
| 262 |
+
"r</w>": 172,
|
| 263 |
+
"t</w>": 173,
|
| 264 |
+
"Į</w>": 174,
|
| 265 |
+
"¿</w>": 175,
|
| 266 |
+
"h</w>": 176,
|
| 267 |
+
"g</w>": 177,
|
| 268 |
+
"m</w>": 178,
|
| 269 |
+
"a</w>": 179,
|
| 270 |
+
"©</w>": 180,
|
| 271 |
+
"y</w>": 181,
|
| 272 |
+
"u</w>": 182,
|
| 273 |
+
"p</w>": 183,
|
| 274 |
+
"i</w>": 184,
|
| 275 |
+
"f</w>": 185,
|
| 276 |
+
"c</w>": 186,
|
| 277 |
+
"l</w>": 187,
|
| 278 |
+
"j</w>": 188,
|
| 279 |
+
"o</w>": 189,
|
| 280 |
+
"IJ</w>": 190,
|
| 281 |
+
"k</w>": 191,
|
| 282 |
+
"w</w>": 192,
|
| 283 |
+
"v</w>": 193,
|
| 284 |
+
"b</w>": 194,
|
| 285 |
+
"Ĺ</w>": 195,
|
| 286 |
+
"x</w>": 196,
|
| 287 |
+
"z</w>": 197,
|
| 288 |
+
"¸</w>": 198,
|
| 289 |
+
"į</w>": 199,
|
| 290 |
+
"ģ</w>": 200,
|
| 291 |
+
"ĺ</w>": 201,
|
| 292 |
+
"«</w>": 202,
|
| 293 |
+
"¢</w>": 203,
|
| 294 |
+
"ł</w>": 204,
|
| 295 |
+
"Ĭ</w>": 205,
|
| 296 |
+
"³</w>": 206,
|
| 297 |
+
"Ń</w>": 207,
|
| 298 |
+
".</w>": 208,
|
| 299 |
+
"ŀ</w>": 209,
|
| 300 |
+
"²</w>": 210,
|
| 301 |
+
"°</w>": 211,
|
| 302 |
+
"µ</w>": 212,
|
| 303 |
+
"ĩ</w>": 213,
|
| 304 |
+
"¾</w>": 214,
|
| 305 |
+
"ĥ</w>": 215,
|
| 306 |
+
"Ĥ</w>": 216,
|
| 307 |
+
"¡</w>": 217,
|
| 308 |
+
"Ķ</w>": 218,
|
| 309 |
+
"¼</w>": 219,
|
| 310 |
+
"¨</w>": 220,
|
| 311 |
+
"ī</w>": 221,
|
| 312 |
+
"Ļ</w>": 222,
|
| 313 |
+
"ħ</w>": 223,
|
| 314 |
+
"Ĩ</w>": 224,
|
| 315 |
+
"®</w>": 225,
|
| 316 |
"¹</w>": 226,
|
| 317 |
+
"Ħ</w>": 227,
|
| 318 |
+
"£</w>": 228,
|
| 319 |
+
"¤</w>": 229,
|
| 320 |
+
"±</w>": 230,
|
| 321 |
+
"¥</w>": 231,
|
| 322 |
+
"Ŀ</w>": 232,
|
| 323 |
+
"¶</w>": 233,
|
| 324 |
+
"ĵ</w>": 234,
|
| 325 |
+
"¯</w>": 235,
|
| 326 |
+
"ĸ</w>": 236,
|
| 327 |
+
"Ģ</w>": 237,
|
| 328 |
+
"§</w>": 238,
|
| 329 |
+
"Ī</w>": 239,
|
| 330 |
+
"5</w>": 240,
|
| 331 |
+
"ľ</w>": 241,
|
| 332 |
+
"]</w>": 242,
|
| 333 |
+
"ķ</w>": 243,
|
| 334 |
+
"q</w>": 244,
|
| 335 |
+
"ĭ</w>": 245,
|
| 336 |
+
"º</w>": 246,
|
| 337 |
+
"½</w>": 247,
|
| 338 |
+
"Ł</w>": 248,
|
| 339 |
+
"/</w>": 249,
|
| 340 |
+
"8</w>": 250,
|
| 341 |
+
"ı</w>": 251,
|
| 342 |
+
"Ľ</w>": 252,
|
| 343 |
+
"¦</w>": 253,
|
| 344 |
+
"Ĵ</w>": 254,
|
| 345 |
+
"></w>": 255,
|
| 346 |
+
"·</w>": 256,
|
| 347 |
+
"-</w>": 257,
|
| 348 |
+
";</w>": 258,
|
| 349 |
+
"»</w>": 259,
|
| 350 |
+
"1</w>": 260,
|
| 351 |
+
"9</w>": 261,
|
| 352 |
+
"ij</w>": 262,
|
| 353 |
+
"¬</w>": 263,
|
| 354 |
+
"`</w>": 264,
|
| 355 |
+
"~</w>": 265,
|
| 356 |
+
":</w>": 266,
|
| 357 |
+
"ļ</w>": 267,
|
| 358 |
+
"'</w>": 268,
|
| 359 |
+
"´</w>": 269,
|
| 360 |
+
"@</w>": 270,
|
| 361 |
+
"_</w>": 271,
|
| 362 |
+
"4</w>": 272,
|
| 363 |
+
")</w>": 273,
|
| 364 |
+
"}</w>": 274,
|
| 365 |
+
"2</w>": 275,
|
| 366 |
+
"(</w>": 276,
|
| 367 |
+
"İ</w>": 277,
|
| 368 |
+
"\\</w>": 278,
|
| 369 |
+
"|</w>": 279,
|
| 370 |
+
"0</w>": 280,
|
| 371 |
+
"+</w>": 281,
|
| 372 |
+
",</w>": 282,
|
| 373 |
+
"<</w>": 283,
|
| 374 |
+
"3</w>": 284,
|
| 375 |
+
"!</w>": 285,
|
| 376 |
+
"#</w>": 286,
|
| 377 |
+
"&</w>": 287,
|
| 378 |
+
"=</w>": 288,
|
| 379 |
+
"[</w>": 289,
|
| 380 |
+
"7</w>": 290,
|
| 381 |
+
"$</w>": 291,
|
| 382 |
+
"6</w>": 292,
|
| 383 |
+
"\"</w>": 293,
|
| 384 |
+
"%</w>": 294,
|
| 385 |
+
"?</w>": 295,
|
| 386 |
+
"*</w>": 296,
|
| 387 |
+
"^</w>": 297,
|
| 388 |
"th": 298,
|
| 389 |
"the</w>": 299,
|
| 390 |
"in": 300,
|
vocab.json
CHANGED
|
@@ -1,91 +1,91 @@
|
|
| 1 |
{
|
| 2 |
"!": 2,
|
| 3 |
-
"!</w>":
|
| 4 |
"\"": 3,
|
| 5 |
-
"\"</w>":
|
| 6 |
"#": 4,
|
| 7 |
-
"#</w>":
|
| 8 |
"$": 5,
|
| 9 |
-
"$</w>":
|
| 10 |
"%": 6,
|
| 11 |
-
"%</w>":
|
| 12 |
"&": 7,
|
| 13 |
-
"&</w>":
|
| 14 |
"'": 8,
|
| 15 |
-
"'</w>":
|
| 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>":
|
| 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>": 226,
|
| 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>": 293,
|
| 6 |
"#": 4,
|
| 7 |
+
"#</w>": 286,
|
| 8 |
"$": 5,
|
| 9 |
+
"$</w>": 291,
|
| 10 |
"%": 6,
|
| 11 |
+
"%</w>": 294,
|
| 12 |
"&": 7,
|
| 13 |
+
"&</w>": 287,
|
| 14 |
"'": 8,
|
| 15 |
+
"'</w>": 268,
|
| 16 |
"'s</w>": 363,
|
| 17 |
"(": 9,
|
| 18 |
+
"(</w>": 276,
|
| 19 |
")": 10,
|
| 20 |
+
")</w>": 273,
|
| 21 |
"*": 11,
|
| 22 |
+
"*</w>": 296,
|
| 23 |
"+": 12,
|
| 24 |
+
"+</w>": 281,
|
| 25 |
",": 13,
|
| 26 |
+
",</w>": 282,
|
| 27 |
",@</w>": 622,
|
| 28 |
"-": 14,
|
| 29 |
+
"-</w>": 257,
|
| 30 |
"-@</w>": 353,
|
| 31 |
".": 15,
|
| 32 |
+
".</w>": 208,
|
| 33 |
".@</w>": 569,
|
| 34 |
"/": 16,
|
| 35 |
+
"/</w>": 249,
|
| 36 |
"0": 17,
|
| 37 |
+
"0</w>": 280,
|
| 38 |
"1": 18,
|
| 39 |
+
"1</w>": 260,
|
| 40 |
"2": 19,
|
| 41 |
+
"2</w>": 275,
|
| 42 |
"3": 20,
|
| 43 |
+
"3</w>": 284,
|
| 44 |
"4": 21,
|
| 45 |
+
"4</w>": 272,
|
| 46 |
"5": 22,
|
| 47 |
+
"5</w>": 240,
|
| 48 |
"6": 23,
|
| 49 |
+
"6</w>": 292,
|
| 50 |
"7": 24,
|
| 51 |
+
"7</w>": 290,
|
| 52 |
"8": 25,
|
| 53 |
+
"8</w>": 250,
|
| 54 |
"9": 26,
|
| 55 |
+
"9</w>": 261,
|
| 56 |
":": 27,
|
| 57 |
+
":</w>": 266,
|
| 58 |
";": 28,
|
| 59 |
+
";</w>": 258,
|
| 60 |
"<": 29,
|
| 61 |
+
"<</w>": 283,
|
| 62 |
"<|endoftext|>": 1,
|
| 63 |
"<|startoftext|>": 0,
|
| 64 |
"=": 30,
|
| 65 |
+
"=</w>": 288,
|
| 66 |
">": 31,
|
| 67 |
+
"></w>": 255,
|
| 68 |
"?": 32,
|
| 69 |
+
"?</w>": 295,
|
| 70 |
"@": 33,
|
| 71 |
"@,@</w>": 623,
|
| 72 |
"@-@</w>": 354,
|
| 73 |
"@.@</w>": 570,
|
| 74 |
+
"@</w>": 270,
|
| 75 |
"[": 34,
|
| 76 |
+
"[</w>": 289,
|
| 77 |
"\\": 35,
|
| 78 |
+
"\\</w>": 278,
|
| 79 |
"]": 36,
|
| 80 |
+
"]</w>": 242,
|
| 81 |
"^": 37,
|
| 82 |
+
"^</w>": 297,
|
| 83 |
"_": 38,
|
| 84 |
+
"_</w>": 271,
|
| 85 |
"`": 39,
|
| 86 |
+
"`</w>": 264,
|
| 87 |
"a": 40,
|
| 88 |
+
"a</w>": 179,
|
| 89 |
"ab": 408,
|
| 90 |
"able</w>": 675,
|
| 91 |
"about</w>": 721,
|
|
|
|
| 158 |
"au": 448,
|
| 159 |
"ause</w>": 997,
|
| 160 |
"b": 41,
|
| 161 |
+
"b</w>": 194,
|
| 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>": 168,
|
| 247 |
"da": 497,
|
| 248 |
"day</w>": 755,
|
| 249 |
"de": 352,
|
|
|
|
| 275 |
"during</w>": 616,
|
| 276 |
"dy</w>": 727,
|
| 277 |
"e": 44,
|
| 278 |
+
"e</w>": 169,
|
| 279 |
"ea": 344,
|
| 280 |
"eam</w>": 1006,
|
| 281 |
"ear": 445,
|
|
|
|
| 326 |
"ever</w>": 754,
|
| 327 |
"ex": 417,
|
| 328 |
"f": 45,
|
| 329 |
+
"f</w>": 185,
|
| 330 |
"fa": 630,
|
| 331 |
"fac": 893,
|
| 332 |
"fe": 484,
|
|
|
|
| 355 |
"ft</w>": 707,
|
| 356 |
"fu": 665,
|
| 357 |
"g": 46,
|
| 358 |
+
"g</w>": 177,
|
| 359 |
"ga": 631,
|
| 360 |
"game</w>": 697,
|
| 361 |
"gan</w>": 835,
|
|
|
|
| 378 |
"gs</w>": 975,
|
| 379 |
"gu": 426,
|
| 380 |
"h": 47,
|
| 381 |
+
"h</w>": 176,
|
| 382 |
"ha": 367,
|
| 383 |
"had</w>": 459,
|
| 384 |
"har": 971,
|
|
|
|
| 400 |
"however</w>": 867,
|
| 401 |
"hu": 993,
|
| 402 |
"i": 48,
|
| 403 |
+
"i</w>": 184,
|
| 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>": 188,
|
| 442 |
"jo": 585,
|
| 443 |
"joh": 941,
|
| 444 |
"ju": 619,
|
| 445 |
"k": 50,
|
| 446 |
+
"k</w>": 191,
|
| 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>": 187,
|
| 456 |
"la": 348,
|
| 457 |
"lan": 606,
|
| 458 |
"land</w>": 561,
|
|
|
|
| 481 |
"lu": 432,
|
| 482 |
"ly</w>": 342,
|
| 483 |
"m": 52,
|
| 484 |
+
"m</w>": 178,
|
| 485 |
"ma": 365,
|
| 486 |
"made</w>": 794,
|
| 487 |
"man": 444,
|
|
|
|
| 508 |
"musi": 808,
|
| 509 |
"music</w>": 961,
|
| 510 |
"n": 53,
|
| 511 |
+
"n</w>": 170,
|
| 512 |
"na": 517,
|
| 513 |
"nam": 810,
|
| 514 |
"national</w>": 849,
|
|
|
|
| 527 |
"num": 763,
|
| 528 |
"number</w>": 924,
|
| 529 |
"o": 54,
|
| 530 |
+
"o</w>": 189,
|
| 531 |
"ob": 909,
|
| 532 |
"oc": 511,
|
| 533 |
"od</w>": 825,
|
|
|
|
| 571 |
"ow": 416,
|
| 572 |
"own</w>": 617,
|
| 573 |
"p": 55,
|
| 574 |
+
"p</w>": 183,
|
| 575 |
"pa": 593,
|
| 576 |
"par": 427,
|
| 577 |
"part</w>": 892,
|
|
|
|
| 604 |
"pu": 485,
|
| 605 |
"publi": 728,
|
| 606 |
"q": 56,
|
| 607 |
+
"q</w>": 244,
|
| 608 |
"qu": 431,
|
| 609 |
"r": 57,
|
| 610 |
+
"r</w>": 172,
|
| 611 |
"ra": 355,
|
| 612 |
"ran": 523,
|
| 613 |
"re": 304,
|
|
|
|
| 629 |
"ru": 419,
|
| 630 |
"ry</w>": 885,
|
| 631 |
"s": 58,
|
| 632 |
+
"s</w>": 167,
|
| 633 |
"sa": 510,
|
| 634 |
"sc": 414,
|
| 635 |
"sch": 775,
|
|
|
|
| 705 |
"sur": 642,
|
| 706 |
"sy": 673,
|
| 707 |
"t": 59,
|
| 708 |
+
"t</w>": 173,
|
| 709 |
"ta": 438,
|
| 710 |
"tain</w>": 1010,
|
| 711 |
"te": 544,
|
|
|
|
| 775 |
"two</w>": 545,
|
| 776 |
"ty</w>": 584,
|
| 777 |
"u": 60,
|
| 778 |
+
"u</w>": 182,
|
| 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>": 192,
|
| 813 |
"wa": 464,
|
| 814 |
"war": 768,
|
| 815 |
"war</w>": 866,
|
|
|
|
| 840 |
"writ": 722,
|
| 841 |
"ws</w>": 953,
|
| 842 |
"x": 63,
|
| 843 |
+
"x</w>": 196,
|
| 844 |
"y": 64,
|
| 845 |
+
"y</w>": 181,
|
| 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>": 197,
|
| 854 |
"zed</w>": 973,
|
| 855 |
"|": 66,
|
| 856 |
+
"|</w>": 279,
|
| 857 |
"}": 67,
|
| 858 |
+
"}</w>": 274,
|
| 859 |
"~": 68,
|
| 860 |
+
"~</w>": 265,
|
| 861 |
"¡": 69,
|
| 862 |
+
"¡</w>": 217,
|
| 863 |
"¢": 70,
|
| 864 |
+
"¢</w>": 203,
|
| 865 |
"£": 71,
|
| 866 |
+
"£</w>": 228,
|
| 867 |
"¤": 72,
|
| 868 |
+
"¤</w>": 229,
|
| 869 |
"¥": 73,
|
| 870 |
+
"¥</w>": 231,
|
| 871 |
"¦": 74,
|
| 872 |
+
"¦</w>": 253,
|
| 873 |
"§": 75,
|
| 874 |
+
"§</w>": 238,
|
| 875 |
"¨": 76,
|
| 876 |
+
"¨</w>": 220,
|
| 877 |
"©": 77,
|
| 878 |
+
"©</w>": 180,
|
| 879 |
"ª": 78,
|
| 880 |
+
"ª</w>": 171,
|
| 881 |
"«": 79,
|
| 882 |
+
"«</w>": 202,
|
| 883 |
"¬": 80,
|
| 884 |
+
"¬</w>": 263,
|
| 885 |
"®": 81,
|
| 886 |
+
"®</w>": 225,
|
| 887 |
"¯": 82,
|
| 888 |
+
"¯</w>": 235,
|
| 889 |
"°": 83,
|
| 890 |
+
"°</w>": 211,
|
| 891 |
"±": 84,
|
| 892 |
+
"±</w>": 230,
|
| 893 |
"²": 85,
|
| 894 |
+
"²</w>": 210,
|
| 895 |
"³": 86,
|
| 896 |
+
"³</w>": 206,
|
| 897 |
"´": 87,
|
| 898 |
+
"´</w>": 269,
|
| 899 |
"µ": 88,
|
| 900 |
+
"µ</w>": 212,
|
| 901 |
"¶": 89,
|
| 902 |
+
"¶</w>": 233,
|
| 903 |
"·": 90,
|
| 904 |
+
"·</w>": 256,
|
| 905 |
"¸": 91,
|
| 906 |
+
"¸</w>": 198,
|
| 907 |
"¹": 92,
|
| 908 |
"¹</w>": 226,
|
| 909 |
"º": 93,
|
| 910 |
+
"º</w>": 246,
|
| 911 |
"»": 94,
|
| 912 |
+
"»</w>": 259,
|
| 913 |
"¼": 95,
|
| 914 |
+
"¼</w>": 219,
|
| 915 |
"½": 96,
|
| 916 |
+
"½</w>": 247,
|
| 917 |
"¾": 97,
|
| 918 |
+
"¾</w>": 214,
|
| 919 |
"¿": 98,
|
| 920 |
+
"¿</w>": 175,
|
| 921 |
"Â": 99,
|
| 922 |
"Ã": 100,
|
| 923 |
"Ä": 101,
|
|
|
|
| 956 |
"ì": 131,
|
| 957 |
"ï": 132,
|
| 958 |
"Ģ": 133,
|
| 959 |
+
"Ģ</w>": 237,
|
| 960 |
"ģ": 134,
|
| 961 |
+
"ģ</w>": 200,
|
| 962 |
"Ĥ": 135,
|
| 963 |
+
"Ĥ</w>": 216,
|
| 964 |
"ĥ": 136,
|
| 965 |
+
"ĥ</w>": 215,
|
| 966 |
"Ħ": 137,
|
| 967 |
+
"Ħ</w>": 227,
|
| 968 |
"ħ": 138,
|
| 969 |
+
"ħ</w>": 223,
|
| 970 |
"Ĩ": 139,
|
| 971 |
+
"Ĩ</w>": 224,
|
| 972 |
"ĩ": 140,
|
| 973 |
+
"ĩ</w>": 213,
|
| 974 |
"Ī": 141,
|
| 975 |
+
"Ī</w>": 239,
|
| 976 |
"ī": 142,
|
| 977 |
+
"ī</w>": 221,
|
| 978 |
"Ĭ": 143,
|
| 979 |
+
"Ĭ</w>": 205,
|
| 980 |
"ĭ": 144,
|
| 981 |
+
"ĭ</w>": 245,
|
| 982 |
"Į": 145,
|
| 983 |
+
"Į</w>": 174,
|
| 984 |
"į": 146,
|
| 985 |
+
"į</w>": 199,
|
| 986 |
"İ": 147,
|
| 987 |
+
"İ</w>": 277,
|
| 988 |
"ı": 148,
|
| 989 |
+
"ı</w>": 251,
|
| 990 |
"IJ": 149,
|
| 991 |
+
"IJ</w>": 190,
|
| 992 |
"ij": 150,
|
| 993 |
+
"ij</w>": 262,
|
| 994 |
"Ĵ": 151,
|
| 995 |
+
"Ĵ</w>": 254,
|
| 996 |
"ĵ": 152,
|
| 997 |
+
"ĵ</w>": 234,
|
| 998 |
"Ķ": 153,
|
| 999 |
+
"Ķ</w>": 218,
|
| 1000 |
"ķ": 154,
|
| 1001 |
+
"ķ</w>": 243,
|
| 1002 |
"ĸ": 155,
|
| 1003 |
+
"ĸ</w>": 236,
|
| 1004 |
"Ĺ": 156,
|
| 1005 |
+
"Ĺ</w>": 195,
|
| 1006 |
"ĺ": 157,
|
| 1007 |
+
"ĺ</w>": 201,
|
| 1008 |
"Ļ": 158,
|
| 1009 |
+
"Ļ</w>": 222,
|
| 1010 |
"ļ": 159,
|
| 1011 |
+
"ļ</w>": 267,
|
| 1012 |
"Ľ": 160,
|
| 1013 |
+
"Ľ</w>": 252,
|
| 1014 |
"ľ": 161,
|
| 1015 |
+
"ľ</w>": 241,
|
| 1016 |
"Ŀ": 162,
|
| 1017 |
+
"Ŀ</w>": 232,
|
| 1018 |
"ŀ": 163,
|
| 1019 |
+
"ŀ</w>": 209,
|
| 1020 |
"Ł": 164,
|
| 1021 |
+
"Ł</w>": 248,
|
| 1022 |
"ł": 165,
|
| 1023 |
+
"ł</w>": 204,
|
| 1024 |
"Ń": 166,
|
| 1025 |
+
"Ń</w>": 207
|
| 1026 |
}
|