Upload folder using huggingface_hub
Browse files
software-BERT_CRF/config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"model_name": "software-BERT_CRF",
|
| 3 |
"architecture": "BERT_CRF",
|
| 4 |
"embeddings_name": null,
|
| 5 |
-
"char_vocab_size":
|
| 6 |
"case_vocab_size": 8,
|
| 7 |
"char_embedding_size": 25,
|
| 8 |
"num_char_lstm_units": 25,
|
|
@@ -35,4 +35,4 @@
|
|
| 35 |
"I-<version>": 8,
|
| 36 |
"O": 9
|
| 37 |
}
|
| 38 |
-
}
|
|
|
|
| 2 |
"model_name": "software-BERT_CRF",
|
| 3 |
"architecture": "BERT_CRF",
|
| 4 |
"embeddings_name": null,
|
| 5 |
+
"char_vocab_size": 549,
|
| 6 |
"case_vocab_size": 8,
|
| 7 |
"char_embedding_size": 25,
|
| 8 |
"num_char_lstm_units": 25,
|
|
|
|
| 35 |
"I-<version>": 8,
|
| 36 |
"O": 9
|
| 37 |
}
|
| 38 |
+
}
|
software-BERT_CRF/model_weights.hdf5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440058504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d06aaf86cddcf53c5a0fa0897958162c80aeae7bbbd2137d3b4e4d284ddc9c8
|
| 3 |
size 440058504
|
software-BERT_CRF/preprocessor.json
CHANGED
|
@@ -113,445 +113,449 @@
|
|
| 113 |
"\u00ab": 103,
|
| 114 |
"\u00ac": 104,
|
| 115 |
"\u00ae": 105,
|
| 116 |
-
"\
|
| 117 |
-
"\
|
| 118 |
-
"\
|
| 119 |
-
"\
|
| 120 |
-
"\
|
| 121 |
-
"\
|
| 122 |
-
"\
|
| 123 |
-
"\
|
| 124 |
-
"\
|
| 125 |
-
"\
|
| 126 |
-
"\
|
| 127 |
-
"\
|
| 128 |
-
"\
|
| 129 |
-
"\
|
| 130 |
-
"\
|
| 131 |
-
"\
|
| 132 |
-
"\
|
| 133 |
-
"\
|
| 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 |
-
"\ud835\
|
| 528 |
-
"\ud835\
|
| 529 |
-
"\ud835\
|
| 530 |
-
"\ud835\
|
| 531 |
-
"\ud835\
|
| 532 |
-
"\ud835\
|
| 533 |
-
"\ud835\
|
| 534 |
-
"\ud835\
|
| 535 |
-
"\ud835\
|
| 536 |
-
"\ud835\
|
| 537 |
-
"\ud835\
|
| 538 |
-
"\ud835\
|
| 539 |
-
"\ud835\
|
| 540 |
-
"\ud835\
|
| 541 |
-
"\ud835\
|
| 542 |
-
"\ud835\
|
| 543 |
-
"\ud835\
|
| 544 |
-
"\ud835\
|
| 545 |
-
"\ud835\
|
| 546 |
-
"\ud835\
|
| 547 |
-
"\ud835\
|
| 548 |
-
"\ud835\
|
| 549 |
-
"\ud835\
|
| 550 |
-
"\ud835\
|
| 551 |
-
"\ud835\
|
| 552 |
-
"\ud835\
|
| 553 |
-
"\ud835\
|
| 554 |
-
"\ud835\
|
|
|
|
|
|
|
|
|
|
|
|
|
| 555 |
},
|
| 556 |
"vocab_tag": {
|
| 557 |
"<PAD>": 0,
|
|
|
|
| 113 |
"\u00ab": 103,
|
| 114 |
"\u00ac": 104,
|
| 115 |
"\u00ae": 105,
|
| 116 |
+
"\u00af": 106,
|
| 117 |
+
"\u00b0": 107,
|
| 118 |
+
"\u00b1": 108,
|
| 119 |
+
"\u00b2": 109,
|
| 120 |
+
"\u00b3": 110,
|
| 121 |
+
"\u00b4": 111,
|
| 122 |
+
"\u00b5": 112,
|
| 123 |
+
"\u00b6": 113,
|
| 124 |
+
"\u00b7": 114,
|
| 125 |
+
"\u00b8": 115,
|
| 126 |
+
"\u00b9": 116,
|
| 127 |
+
"\u00ba": 117,
|
| 128 |
+
"\u00bb": 118,
|
| 129 |
+
"\u00bc": 119,
|
| 130 |
+
"\u00bd": 120,
|
| 131 |
+
"\u00be": 121,
|
| 132 |
+
"\u00bf": 122,
|
| 133 |
+
"\u00c0": 123,
|
| 134 |
+
"\u00c1": 124,
|
| 135 |
+
"\u00c2": 125,
|
| 136 |
+
"\u00c3": 126,
|
| 137 |
+
"\u00c4": 127,
|
| 138 |
+
"\u00c5": 128,
|
| 139 |
+
"\u00c8": 129,
|
| 140 |
+
"\u00c9": 130,
|
| 141 |
+
"\u00ca": 131,
|
| 142 |
+
"\u00cd": 132,
|
| 143 |
+
"\u00d0": 133,
|
| 144 |
+
"\u00d2": 134,
|
| 145 |
+
"\u00d3": 135,
|
| 146 |
+
"\u00d4": 136,
|
| 147 |
+
"\u00d5": 137,
|
| 148 |
+
"\u00d6": 138,
|
| 149 |
+
"\u00d7": 139,
|
| 150 |
+
"\u00d8": 140,
|
| 151 |
+
"\u00d9": 141,
|
| 152 |
+
"\u00da": 142,
|
| 153 |
+
"\u00dc": 143,
|
| 154 |
+
"\u00de": 144,
|
| 155 |
+
"\u00df": 145,
|
| 156 |
+
"\u00e0": 146,
|
| 157 |
+
"\u00e1": 147,
|
| 158 |
+
"\u00e2": 148,
|
| 159 |
+
"\u00e3": 149,
|
| 160 |
+
"\u00e4": 150,
|
| 161 |
+
"\u00e5": 151,
|
| 162 |
+
"\u00e7": 152,
|
| 163 |
+
"\u00e8": 153,
|
| 164 |
+
"\u00e9": 154,
|
| 165 |
+
"\u00ea": 155,
|
| 166 |
+
"\u00eb": 156,
|
| 167 |
+
"\u00ec": 157,
|
| 168 |
+
"\u00ed": 158,
|
| 169 |
+
"\u00ee": 159,
|
| 170 |
+
"\u00ef": 160,
|
| 171 |
+
"\u00f0": 161,
|
| 172 |
+
"\u00f1": 162,
|
| 173 |
+
"\u00f2": 163,
|
| 174 |
+
"\u00f3": 164,
|
| 175 |
+
"\u00f4": 165,
|
| 176 |
+
"\u00f5": 166,
|
| 177 |
+
"\u00f6": 167,
|
| 178 |
+
"\u00f7": 168,
|
| 179 |
+
"\u00f8": 169,
|
| 180 |
+
"\u00f9": 170,
|
| 181 |
+
"\u00fa": 171,
|
| 182 |
+
"\u00fb": 172,
|
| 183 |
+
"\u00fc": 173,
|
| 184 |
+
"\u00fd": 174,
|
| 185 |
+
"\u00fe": 175,
|
| 186 |
+
"\u0100": 176,
|
| 187 |
+
"\u0101": 177,
|
| 188 |
+
"\u0103": 178,
|
| 189 |
+
"\u0105": 179,
|
| 190 |
+
"\u0106": 180,
|
| 191 |
+
"\u0107": 181,
|
| 192 |
+
"\u0108": 182,
|
| 193 |
+
"\u0109": 183,
|
| 194 |
+
"\u010c": 184,
|
| 195 |
+
"\u010d": 185,
|
| 196 |
+
"\u0113": 186,
|
| 197 |
+
"\u0117": 187,
|
| 198 |
+
"\u0118": 188,
|
| 199 |
+
"\u011b": 189,
|
| 200 |
+
"\u012b": 190,
|
| 201 |
+
"\u0130": 191,
|
| 202 |
+
"\u0131": 192,
|
| 203 |
+
"\u013e": 193,
|
| 204 |
+
"\u0142": 194,
|
| 205 |
+
"\u0144": 195,
|
| 206 |
+
"\u0148": 196,
|
| 207 |
+
"\u014d": 197,
|
| 208 |
+
"\u0151": 198,
|
| 209 |
+
"\u0159": 199,
|
| 210 |
+
"\u015a": 200,
|
| 211 |
+
"\u015c": 201,
|
| 212 |
+
"\u015d": 202,
|
| 213 |
+
"\u015e": 203,
|
| 214 |
+
"\u015f": 204,
|
| 215 |
+
"\u0160": 205,
|
| 216 |
+
"\u0161": 206,
|
| 217 |
+
"\u0168": 207,
|
| 218 |
+
"\u0169": 208,
|
| 219 |
+
"\u016b": 209,
|
| 220 |
+
"\u016f": 210,
|
| 221 |
+
"\u0175": 211,
|
| 222 |
+
"\u0176": 212,
|
| 223 |
+
"\u0177": 213,
|
| 224 |
+
"\u017d": 214,
|
| 225 |
+
"\u017e": 215,
|
| 226 |
+
"\u0192": 216,
|
| 227 |
+
"\u01eb": 217,
|
| 228 |
+
"\u021b": 218,
|
| 229 |
+
"\u0251": 219,
|
| 230 |
+
"\u025b": 220,
|
| 231 |
+
"\u0263": 221,
|
| 232 |
+
"\u02a6": 222,
|
| 233 |
+
"\u02b9": 223,
|
| 234 |
+
"\u02bc": 224,
|
| 235 |
+
"\u02c2": 225,
|
| 236 |
+
"\u02c3": 226,
|
| 237 |
+
"\u02c6": 227,
|
| 238 |
+
"\u02c7": 228,
|
| 239 |
+
"\u02c9": 229,
|
| 240 |
+
"\u02d8": 230,
|
| 241 |
+
"\u02d9": 231,
|
| 242 |
+
"\u02da": 232,
|
| 243 |
+
"\u02db": 233,
|
| 244 |
+
"\u02dc": 234,
|
| 245 |
+
"\u0303": 235,
|
| 246 |
+
"\u030a": 236,
|
| 247 |
+
"\u0313": 237,
|
| 248 |
+
"\u0314": 238,
|
| 249 |
+
"\u031d": 239,
|
| 250 |
+
"\u034c": 240,
|
| 251 |
+
"\u0350": 241,
|
| 252 |
+
"\u0351": 242,
|
| 253 |
+
"\u0352": 243,
|
| 254 |
+
"\u0354": 244,
|
| 255 |
+
"\u0357": 245,
|
| 256 |
+
"\u0358": 246,
|
| 257 |
+
"\u0371": 247,
|
| 258 |
+
"\u0374": 248,
|
| 259 |
+
"\u0392": 249,
|
| 260 |
+
"\u0393": 250,
|
| 261 |
+
"\u0394": 251,
|
| 262 |
+
"\u0397": 252,
|
| 263 |
+
"\u0398": 253,
|
| 264 |
+
"\u039b": 254,
|
| 265 |
+
"\u03a0": 255,
|
| 266 |
+
"\u03a3": 256,
|
| 267 |
+
"\u03a4": 257,
|
| 268 |
+
"\u03a5": 258,
|
| 269 |
+
"\u03a6": 259,
|
| 270 |
+
"\u03a7": 260,
|
| 271 |
+
"\u03a8": 261,
|
| 272 |
+
"\u03a9": 262,
|
| 273 |
+
"\u03b1": 263,
|
| 274 |
+
"\u03b2": 264,
|
| 275 |
+
"\u03b3": 265,
|
| 276 |
+
"\u03b4": 266,
|
| 277 |
+
"\u03b5": 267,
|
| 278 |
+
"\u03b6": 268,
|
| 279 |
+
"\u03b7": 269,
|
| 280 |
+
"\u03b8": 270,
|
| 281 |
+
"\u03b9": 271,
|
| 282 |
+
"\u03ba": 272,
|
| 283 |
+
"\u03bb": 273,
|
| 284 |
+
"\u03bc": 274,
|
| 285 |
+
"\u03bd": 275,
|
| 286 |
+
"\u03be": 276,
|
| 287 |
+
"\u03c0": 277,
|
| 288 |
+
"\u03c1": 278,
|
| 289 |
+
"\u03c3": 279,
|
| 290 |
+
"\u03c4": 280,
|
| 291 |
+
"\u03c5": 281,
|
| 292 |
+
"\u03c6": 282,
|
| 293 |
+
"\u03c7": 283,
|
| 294 |
+
"\u03c8": 284,
|
| 295 |
+
"\u03c9": 285,
|
| 296 |
+
"\u03d1": 286,
|
| 297 |
+
"\u03d2": 287,
|
| 298 |
+
"\u03d5": 288,
|
| 299 |
+
"\u03e9": 289,
|
| 300 |
+
"\u03ea": 290,
|
| 301 |
+
"\u03eb": 291,
|
| 302 |
+
"\u03ed": 292,
|
| 303 |
+
"\u03ee": 293,
|
| 304 |
+
"\u03f1": 294,
|
| 305 |
+
"\u03f3": 295,
|
| 306 |
+
"\u03f5": 296,
|
| 307 |
+
"\u03fd": 297,
|
| 308 |
+
"\u03fe": 298,
|
| 309 |
+
"\u0408": 299,
|
| 310 |
+
"\u0412": 300,
|
| 311 |
+
"\u0413": 301,
|
| 312 |
+
"\u041a": 302,
|
| 313 |
+
"\u041d": 303,
|
| 314 |
+
"\u0424": 304,
|
| 315 |
+
"\u0430": 305,
|
| 316 |
+
"\u0545": 306,
|
| 317 |
+
"\u0546": 307,
|
| 318 |
+
"\u0609": 308,
|
| 319 |
+
"\u060a": 309,
|
| 320 |
+
"\u060c": 310,
|
| 321 |
+
"\u060d": 311,
|
| 322 |
+
"\u060e": 312,
|
| 323 |
+
"\u0621": 313,
|
| 324 |
+
"\u0623": 314,
|
| 325 |
+
"\u0626": 315,
|
| 326 |
+
"\u0627": 316,
|
| 327 |
+
"\u0628": 317,
|
| 328 |
+
"\u0629": 318,
|
| 329 |
+
"\u062a": 319,
|
| 330 |
+
"\u062b": 320,
|
| 331 |
+
"\u062d": 321,
|
| 332 |
+
"\u062e": 322,
|
| 333 |
+
"\u062f": 323,
|
| 334 |
+
"\u0631": 324,
|
| 335 |
+
"\u0633": 325,
|
| 336 |
+
"\u0634": 326,
|
| 337 |
+
"\u0637": 327,
|
| 338 |
+
"\u0639": 328,
|
| 339 |
+
"\u0641": 329,
|
| 340 |
+
"\u0642": 330,
|
| 341 |
+
"\u0643": 331,
|
| 342 |
+
"\u0644": 332,
|
| 343 |
+
"\u0645": 333,
|
| 344 |
+
"\u0646": 334,
|
| 345 |
+
"\u0648": 335,
|
| 346 |
+
"\u0649": 336,
|
| 347 |
+
"\u064a": 337,
|
| 348 |
+
"\u064b": 338,
|
| 349 |
+
"\u1e54": 339,
|
| 350 |
+
"\u1e63": 340,
|
| 351 |
+
"\u1e7c": 341,
|
| 352 |
+
"\u1e83": 342,
|
| 353 |
+
"\u1e91": 343,
|
| 354 |
+
"\u1ef9": 344,
|
| 355 |
+
"\u1fb1": 345,
|
| 356 |
+
"\u1fbd": 346,
|
| 357 |
+
"\u2016": 347,
|
| 358 |
+
"\u2020": 348,
|
| 359 |
+
"\u2021": 349,
|
| 360 |
+
"\u2022": 350,
|
| 361 |
+
"\u2026": 351,
|
| 362 |
+
"\u202b": 352,
|
| 363 |
+
"\u202c": 353,
|
| 364 |
+
"\u2030": 354,
|
| 365 |
+
"\u2032": 355,
|
| 366 |
+
"\u2033": 356,
|
| 367 |
+
"\u2034": 357,
|
| 368 |
+
"\u203e": 358,
|
| 369 |
+
"\u2044": 359,
|
| 370 |
+
"\u2074": 360,
|
| 371 |
+
"\u2075": 361,
|
| 372 |
+
"\u2081": 362,
|
| 373 |
+
"\u20a9": 363,
|
| 374 |
+
"\u20ac": 364,
|
| 375 |
+
"\u2103": 365,
|
| 376 |
+
"\u2119": 366,
|
| 377 |
+
"\u211c": 367,
|
| 378 |
+
"\u211d": 368,
|
| 379 |
+
"\u2122": 369,
|
| 380 |
+
"\u2126": 370,
|
| 381 |
+
"\u2150": 371,
|
| 382 |
+
"\u2190": 372,
|
| 383 |
+
"\u2191": 373,
|
| 384 |
+
"\u2192": 374,
|
| 385 |
+
"\u2193": 375,
|
| 386 |
+
"\u21a6": 376,
|
| 387 |
+
"\u21c4": 377,
|
| 388 |
+
"\u21d2": 378,
|
| 389 |
+
"\u21d4": 379,
|
| 390 |
+
"\u2200": 380,
|
| 391 |
+
"\u2202": 381,
|
| 392 |
+
"\u2205": 382,
|
| 393 |
+
"\u2206": 383,
|
| 394 |
+
"\u2208": 384,
|
| 395 |
+
"\u220e": 385,
|
| 396 |
+
"\u2211": 386,
|
| 397 |
+
"\u2212": 387,
|
| 398 |
+
"\u2213": 388,
|
| 399 |
+
"\u2215": 389,
|
| 400 |
+
"\u221a": 390,
|
| 401 |
+
"\u221d": 391,
|
| 402 |
+
"\u221e": 392,
|
| 403 |
+
"\u2229": 393,
|
| 404 |
+
"\u222a": 394,
|
| 405 |
+
"\u222b": 395,
|
| 406 |
+
"\u223c": 396,
|
| 407 |
+
"\u2243": 397,
|
| 408 |
+
"\u2248": 398,
|
| 409 |
+
"\u2260": 399,
|
| 410 |
+
"\u2261": 400,
|
| 411 |
+
"\u2264": 401,
|
| 412 |
+
"\u2265": 402,
|
| 413 |
+
"\u226b": 403,
|
| 414 |
+
"\u227a": 404,
|
| 415 |
+
"\u2282": 405,
|
| 416 |
+
"\u2286": 406,
|
| 417 |
+
"\u2295": 407,
|
| 418 |
+
"\u22a5": 408,
|
| 419 |
+
"\u22c5": 409,
|
| 420 |
+
"\u22ef": 410,
|
| 421 |
+
"\u2329": 411,
|
| 422 |
+
"\u232a": 412,
|
| 423 |
+
"\u232c": 413,
|
| 424 |
+
"\u2338": 414,
|
| 425 |
+
"\u233a": 415,
|
| 426 |
+
"\u233d": 416,
|
| 427 |
+
"\u239b": 417,
|
| 428 |
+
"\u239d": 418,
|
| 429 |
+
"\u239e": 419,
|
| 430 |
+
"\u23a0": 420,
|
| 431 |
+
"\u2423": 421,
|
| 432 |
+
"\u2424": 422,
|
| 433 |
+
"\u2425": 423,
|
| 434 |
+
"\u2426": 424,
|
| 435 |
+
"\u2440": 425,
|
| 436 |
+
"\u24c7": 426,
|
| 437 |
+
"\u2500": 427,
|
| 438 |
+
"\u2502": 428,
|
| 439 |
+
"\u25a0": 429,
|
| 440 |
+
"\u25a1": 430,
|
| 441 |
+
"\u25aa": 431,
|
| 442 |
+
"\u25ab": 432,
|
| 443 |
+
"\u25b2": 433,
|
| 444 |
+
"\u25b3": 434,
|
| 445 |
+
"\u25b5": 435,
|
| 446 |
+
"\u25b6": 436,
|
| 447 |
+
"\u25b8": 437,
|
| 448 |
+
"\u25c6": 438,
|
| 449 |
+
"\u25c7": 439,
|
| 450 |
+
"\u2605": 440,
|
| 451 |
+
"\u2610": 441,
|
| 452 |
+
"\u2713": 442,
|
| 453 |
+
"\u274f": 443,
|
| 454 |
+
"\u29cb": 444,
|
| 455 |
+
"\u2a7d": 445,
|
| 456 |
+
"\u2a7e": 446,
|
| 457 |
+
"\u3008": 447,
|
| 458 |
+
"\u3009": 448,
|
| 459 |
+
"\ue023": 449,
|
| 460 |
+
"\ue024": 450,
|
| 461 |
+
"\ue02c": 451,
|
| 462 |
+
"\ue02e": 452,
|
| 463 |
+
"\ue032": 453,
|
| 464 |
+
"\ue039": 454,
|
| 465 |
+
"\ue044": 455,
|
| 466 |
+
"\ue061": 456,
|
| 467 |
+
"\ue062": 457,
|
| 468 |
+
"\ue067": 458,
|
| 469 |
+
"\ue06b": 459,
|
| 470 |
+
"\ue06c": 460,
|
| 471 |
+
"\ue06d": 461,
|
| 472 |
+
"\ue06e": 462,
|
| 473 |
+
"\ue073": 463,
|
| 474 |
+
"\ue074": 464,
|
| 475 |
+
"\ue07a": 465,
|
| 476 |
+
"\ue093": 466,
|
| 477 |
+
"\ue09d": 467,
|
| 478 |
+
"\ue103": 468,
|
| 479 |
+
"\ue104": 469,
|
| 480 |
+
"\uf03c": 470,
|
| 481 |
+
"\uf043": 471,
|
| 482 |
+
"\uf061": 472,
|
| 483 |
+
"\uf062": 473,
|
| 484 |
+
"\uf063": 474,
|
| 485 |
+
"\uf065": 475,
|
| 486 |
+
"\uf067": 476,
|
| 487 |
+
"\uf06b": 477,
|
| 488 |
+
"\uf06c": 478,
|
| 489 |
+
"\uf06d": 479,
|
| 490 |
+
"\uf070": 480,
|
| 491 |
+
"\uf073": 481,
|
| 492 |
+
"\uf074": 482,
|
| 493 |
+
"\uf077": 483,
|
| 494 |
+
"\uf0a2": 484,
|
| 495 |
+
"\uf0a3": 485,
|
| 496 |
+
"\uf0b0": 486,
|
| 497 |
+
"\uf0b1": 487,
|
| 498 |
+
"\uf0b4": 488,
|
| 499 |
+
"\uf0b7": 489,
|
| 500 |
+
"\uf0b9": 490,
|
| 501 |
+
"\uf0bb": 491,
|
| 502 |
+
"\uf0e2": 492,
|
| 503 |
+
"\uf0e4": 493,
|
| 504 |
+
"\uf0fc": 494,
|
| 505 |
+
"\uf643": 495,
|
| 506 |
+
"\uf644": 496,
|
| 507 |
+
"\uf645": 497,
|
| 508 |
+
"\uf646": 498,
|
| 509 |
+
"\uf647": 499,
|
| 510 |
+
"\uf648": 500,
|
| 511 |
+
"\uf649": 501,
|
| 512 |
+
"\uf64a": 502,
|
| 513 |
+
"\uf64b": 503,
|
| 514 |
+
"\uf64c": 504,
|
| 515 |
+
"\uf6f6": 505,
|
| 516 |
+
"\uf76a": 506,
|
| 517 |
+
"\uf76d": 507,
|
| 518 |
+
"\uf775": 508,
|
| 519 |
+
"\uf777": 509,
|
| 520 |
+
"\uf8e8": 510,
|
| 521 |
+
"\uff0b": 511,
|
| 522 |
+
"\uff0c": 512,
|
| 523 |
+
"\uff1a": 513,
|
| 524 |
+
"\uff1c": 514,
|
| 525 |
+
"\uff1e": 515,
|
| 526 |
+
"\ufffd": 516,
|
| 527 |
+
"\ud835\udc34": 517,
|
| 528 |
+
"\ud835\udc36": 518,
|
| 529 |
+
"\ud835\udc37": 519,
|
| 530 |
+
"\ud835\udc39": 520,
|
| 531 |
+
"\ud835\udc3a": 521,
|
| 532 |
+
"\ud835\udc3b": 522,
|
| 533 |
+
"\ud835\udc3e": 523,
|
| 534 |
+
"\ud835\udc3f": 524,
|
| 535 |
+
"\ud835\udc42": 525,
|
| 536 |
+
"\ud835\udc43": 526,
|
| 537 |
+
"\ud835\udc51": 527,
|
| 538 |
+
"\ud835\udc53": 528,
|
| 539 |
+
"\ud835\udc54": 529,
|
| 540 |
+
"\ud835\udc56": 530,
|
| 541 |
+
"\ud835\udc57": 531,
|
| 542 |
+
"\ud835\udc58": 532,
|
| 543 |
+
"\ud835\udc5e": 533,
|
| 544 |
+
"\ud835\udc5f": 534,
|
| 545 |
+
"\ud835\udc61": 535,
|
| 546 |
+
"\ud835\udc63": 536,
|
| 547 |
+
"\ud835\udd3c": 537,
|
| 548 |
+
"\ud835\udd40": 538,
|
| 549 |
+
"\ud835\udefc": 539,
|
| 550 |
+
"\ud835\udefd": 540,
|
| 551 |
+
"\ud835\udefe": 541,
|
| 552 |
+
"\ud835\udeff": 542,
|
| 553 |
+
"\ud835\udf03": 543,
|
| 554 |
+
"\ud835\udf06": 544,
|
| 555 |
+
"\ud835\udf07": 545,
|
| 556 |
+
"\ud835\udf0b": 546,
|
| 557 |
+
"\ud835\udf0d": 547,
|
| 558 |
+
"\ud835\udf15": 548
|
| 559 |
},
|
| 560 |
"vocab_tag": {
|
| 561 |
"<PAD>": 0,
|