Tokenizer fix
#1
by
justinbarton
- opened
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -826
special_tokens_map.json
CHANGED
|
@@ -101,25 +101,7 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
-
"eos_token":
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
"normalized": false,
|
| 108 |
-
"rstrip": false,
|
| 109 |
-
"single_word": false
|
| 110 |
-
},
|
| 111 |
-
"pad_token": {
|
| 112 |
-
"content": "<pad>",
|
| 113 |
-
"lstrip": false,
|
| 114 |
-
"normalized": false,
|
| 115 |
-
"rstrip": false,
|
| 116 |
-
"single_word": false
|
| 117 |
-
},
|
| 118 |
-
"unk_token": {
|
| 119 |
-
"content": "<unk>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": false,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false
|
| 124 |
-
}
|
| 125 |
}
|
|
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,830 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<pad>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "</s>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "<unk>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"28": {
|
| 28 |
-
"content": "<extra_id_99>",
|
| 29 |
-
"lstrip": true,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": true,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"29": {
|
| 36 |
-
"content": "<extra_id_98>",
|
| 37 |
-
"lstrip": true,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": true,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"30": {
|
| 44 |
-
"content": "<extra_id_97>",
|
| 45 |
-
"lstrip": true,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": true,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"31": {
|
| 52 |
-
"content": "<extra_id_96>",
|
| 53 |
-
"lstrip": true,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": true,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
-
},
|
| 59 |
-
"32": {
|
| 60 |
-
"content": "<extra_id_95>",
|
| 61 |
-
"lstrip": true,
|
| 62 |
-
"normalized": false,
|
| 63 |
-
"rstrip": true,
|
| 64 |
-
"single_word": false,
|
| 65 |
-
"special": true
|
| 66 |
-
},
|
| 67 |
-
"33": {
|
| 68 |
-
"content": "<extra_id_94>",
|
| 69 |
-
"lstrip": true,
|
| 70 |
-
"normalized": false,
|
| 71 |
-
"rstrip": true,
|
| 72 |
-
"single_word": false,
|
| 73 |
-
"special": true
|
| 74 |
-
},
|
| 75 |
-
"34": {
|
| 76 |
-
"content": "<extra_id_93>",
|
| 77 |
-
"lstrip": true,
|
| 78 |
-
"normalized": false,
|
| 79 |
-
"rstrip": true,
|
| 80 |
-
"single_word": false,
|
| 81 |
-
"special": true
|
| 82 |
-
},
|
| 83 |
-
"35": {
|
| 84 |
-
"content": "<extra_id_92>",
|
| 85 |
-
"lstrip": true,
|
| 86 |
-
"normalized": false,
|
| 87 |
-
"rstrip": true,
|
| 88 |
-
"single_word": false,
|
| 89 |
-
"special": true
|
| 90 |
-
},
|
| 91 |
-
"36": {
|
| 92 |
-
"content": "<extra_id_91>",
|
| 93 |
-
"lstrip": true,
|
| 94 |
-
"normalized": false,
|
| 95 |
-
"rstrip": true,
|
| 96 |
-
"single_word": false,
|
| 97 |
-
"special": true
|
| 98 |
-
},
|
| 99 |
-
"37": {
|
| 100 |
-
"content": "<extra_id_90>",
|
| 101 |
-
"lstrip": true,
|
| 102 |
-
"normalized": false,
|
| 103 |
-
"rstrip": true,
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"special": true
|
| 106 |
-
},
|
| 107 |
-
"38": {
|
| 108 |
-
"content": "<extra_id_89>",
|
| 109 |
-
"lstrip": true,
|
| 110 |
-
"normalized": false,
|
| 111 |
-
"rstrip": true,
|
| 112 |
-
"single_word": false,
|
| 113 |
-
"special": true
|
| 114 |
-
},
|
| 115 |
-
"39": {
|
| 116 |
-
"content": "<extra_id_88>",
|
| 117 |
-
"lstrip": true,
|
| 118 |
-
"normalized": false,
|
| 119 |
-
"rstrip": true,
|
| 120 |
-
"single_word": false,
|
| 121 |
-
"special": true
|
| 122 |
-
},
|
| 123 |
-
"40": {
|
| 124 |
-
"content": "<extra_id_87>",
|
| 125 |
-
"lstrip": true,
|
| 126 |
-
"normalized": false,
|
| 127 |
-
"rstrip": true,
|
| 128 |
-
"single_word": false,
|
| 129 |
-
"special": true
|
| 130 |
-
},
|
| 131 |
-
"41": {
|
| 132 |
-
"content": "<extra_id_86>",
|
| 133 |
-
"lstrip": true,
|
| 134 |
-
"normalized": false,
|
| 135 |
-
"rstrip": true,
|
| 136 |
-
"single_word": false,
|
| 137 |
-
"special": true
|
| 138 |
-
},
|
| 139 |
-
"42": {
|
| 140 |
-
"content": "<extra_id_85>",
|
| 141 |
-
"lstrip": true,
|
| 142 |
-
"normalized": false,
|
| 143 |
-
"rstrip": true,
|
| 144 |
-
"single_word": false,
|
| 145 |
-
"special": true
|
| 146 |
-
},
|
| 147 |
-
"43": {
|
| 148 |
-
"content": "<extra_id_84>",
|
| 149 |
-
"lstrip": true,
|
| 150 |
-
"normalized": false,
|
| 151 |
-
"rstrip": true,
|
| 152 |
-
"single_word": false,
|
| 153 |
-
"special": true
|
| 154 |
-
},
|
| 155 |
-
"44": {
|
| 156 |
-
"content": "<extra_id_83>",
|
| 157 |
-
"lstrip": true,
|
| 158 |
-
"normalized": false,
|
| 159 |
-
"rstrip": true,
|
| 160 |
-
"single_word": false,
|
| 161 |
-
"special": true
|
| 162 |
-
},
|
| 163 |
-
"45": {
|
| 164 |
-
"content": "<extra_id_82>",
|
| 165 |
-
"lstrip": true,
|
| 166 |
-
"normalized": false,
|
| 167 |
-
"rstrip": true,
|
| 168 |
-
"single_word": false,
|
| 169 |
-
"special": true
|
| 170 |
-
},
|
| 171 |
-
"46": {
|
| 172 |
-
"content": "<extra_id_81>",
|
| 173 |
-
"lstrip": true,
|
| 174 |
-
"normalized": false,
|
| 175 |
-
"rstrip": true,
|
| 176 |
-
"single_word": false,
|
| 177 |
-
"special": true
|
| 178 |
-
},
|
| 179 |
-
"47": {
|
| 180 |
-
"content": "<extra_id_80>",
|
| 181 |
-
"lstrip": true,
|
| 182 |
-
"normalized": false,
|
| 183 |
-
"rstrip": true,
|
| 184 |
-
"single_word": false,
|
| 185 |
-
"special": true
|
| 186 |
-
},
|
| 187 |
-
"48": {
|
| 188 |
-
"content": "<extra_id_79>",
|
| 189 |
-
"lstrip": true,
|
| 190 |
-
"normalized": false,
|
| 191 |
-
"rstrip": true,
|
| 192 |
-
"single_word": false,
|
| 193 |
-
"special": true
|
| 194 |
-
},
|
| 195 |
-
"49": {
|
| 196 |
-
"content": "<extra_id_78>",
|
| 197 |
-
"lstrip": true,
|
| 198 |
-
"normalized": false,
|
| 199 |
-
"rstrip": true,
|
| 200 |
-
"single_word": false,
|
| 201 |
-
"special": true
|
| 202 |
-
},
|
| 203 |
-
"50": {
|
| 204 |
-
"content": "<extra_id_77>",
|
| 205 |
-
"lstrip": true,
|
| 206 |
-
"normalized": false,
|
| 207 |
-
"rstrip": true,
|
| 208 |
-
"single_word": false,
|
| 209 |
-
"special": true
|
| 210 |
-
},
|
| 211 |
-
"51": {
|
| 212 |
-
"content": "<extra_id_76>",
|
| 213 |
-
"lstrip": true,
|
| 214 |
-
"normalized": false,
|
| 215 |
-
"rstrip": true,
|
| 216 |
-
"single_word": false,
|
| 217 |
-
"special": true
|
| 218 |
-
},
|
| 219 |
-
"52": {
|
| 220 |
-
"content": "<extra_id_75>",
|
| 221 |
-
"lstrip": true,
|
| 222 |
-
"normalized": false,
|
| 223 |
-
"rstrip": true,
|
| 224 |
-
"single_word": false,
|
| 225 |
-
"special": true
|
| 226 |
-
},
|
| 227 |
-
"53": {
|
| 228 |
-
"content": "<extra_id_74>",
|
| 229 |
-
"lstrip": true,
|
| 230 |
-
"normalized": false,
|
| 231 |
-
"rstrip": true,
|
| 232 |
-
"single_word": false,
|
| 233 |
-
"special": true
|
| 234 |
-
},
|
| 235 |
-
"54": {
|
| 236 |
-
"content": "<extra_id_73>",
|
| 237 |
-
"lstrip": true,
|
| 238 |
-
"normalized": false,
|
| 239 |
-
"rstrip": true,
|
| 240 |
-
"single_word": false,
|
| 241 |
-
"special": true
|
| 242 |
-
},
|
| 243 |
-
"55": {
|
| 244 |
-
"content": "<extra_id_72>",
|
| 245 |
-
"lstrip": true,
|
| 246 |
-
"normalized": false,
|
| 247 |
-
"rstrip": true,
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"special": true
|
| 250 |
-
},
|
| 251 |
-
"56": {
|
| 252 |
-
"content": "<extra_id_71>",
|
| 253 |
-
"lstrip": true,
|
| 254 |
-
"normalized": false,
|
| 255 |
-
"rstrip": true,
|
| 256 |
-
"single_word": false,
|
| 257 |
-
"special": true
|
| 258 |
-
},
|
| 259 |
-
"57": {
|
| 260 |
-
"content": "<extra_id_70>",
|
| 261 |
-
"lstrip": true,
|
| 262 |
-
"normalized": false,
|
| 263 |
-
"rstrip": true,
|
| 264 |
-
"single_word": false,
|
| 265 |
-
"special": true
|
| 266 |
-
},
|
| 267 |
-
"58": {
|
| 268 |
-
"content": "<extra_id_69>",
|
| 269 |
-
"lstrip": true,
|
| 270 |
-
"normalized": false,
|
| 271 |
-
"rstrip": true,
|
| 272 |
-
"single_word": false,
|
| 273 |
-
"special": true
|
| 274 |
-
},
|
| 275 |
-
"59": {
|
| 276 |
-
"content": "<extra_id_68>",
|
| 277 |
-
"lstrip": true,
|
| 278 |
-
"normalized": false,
|
| 279 |
-
"rstrip": true,
|
| 280 |
-
"single_word": false,
|
| 281 |
-
"special": true
|
| 282 |
-
},
|
| 283 |
-
"60": {
|
| 284 |
-
"content": "<extra_id_67>",
|
| 285 |
-
"lstrip": true,
|
| 286 |
-
"normalized": false,
|
| 287 |
-
"rstrip": true,
|
| 288 |
-
"single_word": false,
|
| 289 |
-
"special": true
|
| 290 |
-
},
|
| 291 |
-
"61": {
|
| 292 |
-
"content": "<extra_id_66>",
|
| 293 |
-
"lstrip": true,
|
| 294 |
-
"normalized": false,
|
| 295 |
-
"rstrip": true,
|
| 296 |
-
"single_word": false,
|
| 297 |
-
"special": true
|
| 298 |
-
},
|
| 299 |
-
"62": {
|
| 300 |
-
"content": "<extra_id_65>",
|
| 301 |
-
"lstrip": true,
|
| 302 |
-
"normalized": false,
|
| 303 |
-
"rstrip": true,
|
| 304 |
-
"single_word": false,
|
| 305 |
-
"special": true
|
| 306 |
-
},
|
| 307 |
-
"63": {
|
| 308 |
-
"content": "<extra_id_64>",
|
| 309 |
-
"lstrip": true,
|
| 310 |
-
"normalized": false,
|
| 311 |
-
"rstrip": true,
|
| 312 |
-
"single_word": false,
|
| 313 |
-
"special": true
|
| 314 |
-
},
|
| 315 |
-
"64": {
|
| 316 |
-
"content": "<extra_id_63>",
|
| 317 |
-
"lstrip": true,
|
| 318 |
-
"normalized": false,
|
| 319 |
-
"rstrip": true,
|
| 320 |
-
"single_word": false,
|
| 321 |
-
"special": true
|
| 322 |
-
},
|
| 323 |
-
"65": {
|
| 324 |
-
"content": "<extra_id_62>",
|
| 325 |
-
"lstrip": true,
|
| 326 |
-
"normalized": false,
|
| 327 |
-
"rstrip": true,
|
| 328 |
-
"single_word": false,
|
| 329 |
-
"special": true
|
| 330 |
-
},
|
| 331 |
-
"66": {
|
| 332 |
-
"content": "<extra_id_61>",
|
| 333 |
-
"lstrip": true,
|
| 334 |
-
"normalized": false,
|
| 335 |
-
"rstrip": true,
|
| 336 |
-
"single_word": false,
|
| 337 |
-
"special": true
|
| 338 |
-
},
|
| 339 |
-
"67": {
|
| 340 |
-
"content": "<extra_id_60>",
|
| 341 |
-
"lstrip": true,
|
| 342 |
-
"normalized": false,
|
| 343 |
-
"rstrip": true,
|
| 344 |
-
"single_word": false,
|
| 345 |
-
"special": true
|
| 346 |
-
},
|
| 347 |
-
"68": {
|
| 348 |
-
"content": "<extra_id_59>",
|
| 349 |
-
"lstrip": true,
|
| 350 |
-
"normalized": false,
|
| 351 |
-
"rstrip": true,
|
| 352 |
-
"single_word": false,
|
| 353 |
-
"special": true
|
| 354 |
-
},
|
| 355 |
-
"69": {
|
| 356 |
-
"content": "<extra_id_58>",
|
| 357 |
-
"lstrip": true,
|
| 358 |
-
"normalized": false,
|
| 359 |
-
"rstrip": true,
|
| 360 |
-
"single_word": false,
|
| 361 |
-
"special": true
|
| 362 |
-
},
|
| 363 |
-
"70": {
|
| 364 |
-
"content": "<extra_id_57>",
|
| 365 |
-
"lstrip": true,
|
| 366 |
-
"normalized": false,
|
| 367 |
-
"rstrip": true,
|
| 368 |
-
"single_word": false,
|
| 369 |
-
"special": true
|
| 370 |
-
},
|
| 371 |
-
"71": {
|
| 372 |
-
"content": "<extra_id_56>",
|
| 373 |
-
"lstrip": true,
|
| 374 |
-
"normalized": false,
|
| 375 |
-
"rstrip": true,
|
| 376 |
-
"single_word": false,
|
| 377 |
-
"special": true
|
| 378 |
-
},
|
| 379 |
-
"72": {
|
| 380 |
-
"content": "<extra_id_55>",
|
| 381 |
-
"lstrip": true,
|
| 382 |
-
"normalized": false,
|
| 383 |
-
"rstrip": true,
|
| 384 |
-
"single_word": false,
|
| 385 |
-
"special": true
|
| 386 |
-
},
|
| 387 |
-
"73": {
|
| 388 |
-
"content": "<extra_id_54>",
|
| 389 |
-
"lstrip": true,
|
| 390 |
-
"normalized": false,
|
| 391 |
-
"rstrip": true,
|
| 392 |
-
"single_word": false,
|
| 393 |
-
"special": true
|
| 394 |
-
},
|
| 395 |
-
"74": {
|
| 396 |
-
"content": "<extra_id_53>",
|
| 397 |
-
"lstrip": true,
|
| 398 |
-
"normalized": false,
|
| 399 |
-
"rstrip": true,
|
| 400 |
-
"single_word": false,
|
| 401 |
-
"special": true
|
| 402 |
-
},
|
| 403 |
-
"75": {
|
| 404 |
-
"content": "<extra_id_52>",
|
| 405 |
-
"lstrip": true,
|
| 406 |
-
"normalized": false,
|
| 407 |
-
"rstrip": true,
|
| 408 |
-
"single_word": false,
|
| 409 |
-
"special": true
|
| 410 |
-
},
|
| 411 |
-
"76": {
|
| 412 |
-
"content": "<extra_id_51>",
|
| 413 |
-
"lstrip": true,
|
| 414 |
-
"normalized": false,
|
| 415 |
-
"rstrip": true,
|
| 416 |
-
"single_word": false,
|
| 417 |
-
"special": true
|
| 418 |
-
},
|
| 419 |
-
"77": {
|
| 420 |
-
"content": "<extra_id_50>",
|
| 421 |
-
"lstrip": true,
|
| 422 |
-
"normalized": false,
|
| 423 |
-
"rstrip": true,
|
| 424 |
-
"single_word": false,
|
| 425 |
-
"special": true
|
| 426 |
-
},
|
| 427 |
-
"78": {
|
| 428 |
-
"content": "<extra_id_49>",
|
| 429 |
-
"lstrip": true,
|
| 430 |
-
"normalized": false,
|
| 431 |
-
"rstrip": true,
|
| 432 |
-
"single_word": false,
|
| 433 |
-
"special": true
|
| 434 |
-
},
|
| 435 |
-
"79": {
|
| 436 |
-
"content": "<extra_id_48>",
|
| 437 |
-
"lstrip": true,
|
| 438 |
-
"normalized": false,
|
| 439 |
-
"rstrip": true,
|
| 440 |
-
"single_word": false,
|
| 441 |
-
"special": true
|
| 442 |
-
},
|
| 443 |
-
"80": {
|
| 444 |
-
"content": "<extra_id_47>",
|
| 445 |
-
"lstrip": true,
|
| 446 |
-
"normalized": false,
|
| 447 |
-
"rstrip": true,
|
| 448 |
-
"single_word": false,
|
| 449 |
-
"special": true
|
| 450 |
-
},
|
| 451 |
-
"81": {
|
| 452 |
-
"content": "<extra_id_46>",
|
| 453 |
-
"lstrip": true,
|
| 454 |
-
"normalized": false,
|
| 455 |
-
"rstrip": true,
|
| 456 |
-
"single_word": false,
|
| 457 |
-
"special": true
|
| 458 |
-
},
|
| 459 |
-
"82": {
|
| 460 |
-
"content": "<extra_id_45>",
|
| 461 |
-
"lstrip": true,
|
| 462 |
-
"normalized": false,
|
| 463 |
-
"rstrip": true,
|
| 464 |
-
"single_word": false,
|
| 465 |
-
"special": true
|
| 466 |
-
},
|
| 467 |
-
"83": {
|
| 468 |
-
"content": "<extra_id_44>",
|
| 469 |
-
"lstrip": true,
|
| 470 |
-
"normalized": false,
|
| 471 |
-
"rstrip": true,
|
| 472 |
-
"single_word": false,
|
| 473 |
-
"special": true
|
| 474 |
-
},
|
| 475 |
-
"84": {
|
| 476 |
-
"content": "<extra_id_43>",
|
| 477 |
-
"lstrip": true,
|
| 478 |
-
"normalized": false,
|
| 479 |
-
"rstrip": true,
|
| 480 |
-
"single_word": false,
|
| 481 |
-
"special": true
|
| 482 |
-
},
|
| 483 |
-
"85": {
|
| 484 |
-
"content": "<extra_id_42>",
|
| 485 |
-
"lstrip": true,
|
| 486 |
-
"normalized": false,
|
| 487 |
-
"rstrip": true,
|
| 488 |
-
"single_word": false,
|
| 489 |
-
"special": true
|
| 490 |
-
},
|
| 491 |
-
"86": {
|
| 492 |
-
"content": "<extra_id_41>",
|
| 493 |
-
"lstrip": true,
|
| 494 |
-
"normalized": false,
|
| 495 |
-
"rstrip": true,
|
| 496 |
-
"single_word": false,
|
| 497 |
-
"special": true
|
| 498 |
-
},
|
| 499 |
-
"87": {
|
| 500 |
-
"content": "<extra_id_40>",
|
| 501 |
-
"lstrip": true,
|
| 502 |
-
"normalized": false,
|
| 503 |
-
"rstrip": true,
|
| 504 |
-
"single_word": false,
|
| 505 |
-
"special": true
|
| 506 |
-
},
|
| 507 |
-
"88": {
|
| 508 |
-
"content": "<extra_id_39>",
|
| 509 |
-
"lstrip": true,
|
| 510 |
-
"normalized": false,
|
| 511 |
-
"rstrip": true,
|
| 512 |
-
"single_word": false,
|
| 513 |
-
"special": true
|
| 514 |
-
},
|
| 515 |
-
"89": {
|
| 516 |
-
"content": "<extra_id_38>",
|
| 517 |
-
"lstrip": true,
|
| 518 |
-
"normalized": false,
|
| 519 |
-
"rstrip": true,
|
| 520 |
-
"single_word": false,
|
| 521 |
-
"special": true
|
| 522 |
-
},
|
| 523 |
-
"90": {
|
| 524 |
-
"content": "<extra_id_37>",
|
| 525 |
-
"lstrip": true,
|
| 526 |
-
"normalized": false,
|
| 527 |
-
"rstrip": true,
|
| 528 |
-
"single_word": false,
|
| 529 |
-
"special": true
|
| 530 |
-
},
|
| 531 |
-
"91": {
|
| 532 |
-
"content": "<extra_id_36>",
|
| 533 |
-
"lstrip": true,
|
| 534 |
-
"normalized": false,
|
| 535 |
-
"rstrip": true,
|
| 536 |
-
"single_word": false,
|
| 537 |
-
"special": true
|
| 538 |
-
},
|
| 539 |
-
"92": {
|
| 540 |
-
"content": "<extra_id_35>",
|
| 541 |
-
"lstrip": true,
|
| 542 |
-
"normalized": false,
|
| 543 |
-
"rstrip": true,
|
| 544 |
-
"single_word": false,
|
| 545 |
-
"special": true
|
| 546 |
-
},
|
| 547 |
-
"93": {
|
| 548 |
-
"content": "<extra_id_34>",
|
| 549 |
-
"lstrip": true,
|
| 550 |
-
"normalized": false,
|
| 551 |
-
"rstrip": true,
|
| 552 |
-
"single_word": false,
|
| 553 |
-
"special": true
|
| 554 |
-
},
|
| 555 |
-
"94": {
|
| 556 |
-
"content": "<extra_id_33>",
|
| 557 |
-
"lstrip": true,
|
| 558 |
-
"normalized": false,
|
| 559 |
-
"rstrip": true,
|
| 560 |
-
"single_word": false,
|
| 561 |
-
"special": true
|
| 562 |
-
},
|
| 563 |
-
"95": {
|
| 564 |
-
"content": "<extra_id_32>",
|
| 565 |
-
"lstrip": true,
|
| 566 |
-
"normalized": false,
|
| 567 |
-
"rstrip": true,
|
| 568 |
-
"single_word": false,
|
| 569 |
-
"special": true
|
| 570 |
-
},
|
| 571 |
-
"96": {
|
| 572 |
-
"content": "<extra_id_31>",
|
| 573 |
-
"lstrip": true,
|
| 574 |
-
"normalized": false,
|
| 575 |
-
"rstrip": true,
|
| 576 |
-
"single_word": false,
|
| 577 |
-
"special": true
|
| 578 |
-
},
|
| 579 |
-
"97": {
|
| 580 |
-
"content": "<extra_id_30>",
|
| 581 |
-
"lstrip": true,
|
| 582 |
-
"normalized": false,
|
| 583 |
-
"rstrip": true,
|
| 584 |
-
"single_word": false,
|
| 585 |
-
"special": true
|
| 586 |
-
},
|
| 587 |
-
"98": {
|
| 588 |
-
"content": "<extra_id_29>",
|
| 589 |
-
"lstrip": true,
|
| 590 |
-
"normalized": false,
|
| 591 |
-
"rstrip": true,
|
| 592 |
-
"single_word": false,
|
| 593 |
-
"special": true
|
| 594 |
-
},
|
| 595 |
-
"99": {
|
| 596 |
-
"content": "<extra_id_28>",
|
| 597 |
-
"lstrip": true,
|
| 598 |
-
"normalized": false,
|
| 599 |
-
"rstrip": true,
|
| 600 |
-
"single_word": false,
|
| 601 |
-
"special": true
|
| 602 |
-
},
|
| 603 |
-
"100": {
|
| 604 |
-
"content": "<extra_id_27>",
|
| 605 |
-
"lstrip": true,
|
| 606 |
-
"normalized": false,
|
| 607 |
-
"rstrip": true,
|
| 608 |
-
"single_word": false,
|
| 609 |
-
"special": true
|
| 610 |
-
},
|
| 611 |
-
"101": {
|
| 612 |
-
"content": "<extra_id_26>",
|
| 613 |
-
"lstrip": true,
|
| 614 |
-
"normalized": false,
|
| 615 |
-
"rstrip": true,
|
| 616 |
-
"single_word": false,
|
| 617 |
-
"special": true
|
| 618 |
-
},
|
| 619 |
-
"102": {
|
| 620 |
-
"content": "<extra_id_25>",
|
| 621 |
-
"lstrip": true,
|
| 622 |
-
"normalized": false,
|
| 623 |
-
"rstrip": true,
|
| 624 |
-
"single_word": false,
|
| 625 |
-
"special": true
|
| 626 |
-
},
|
| 627 |
-
"103": {
|
| 628 |
-
"content": "<extra_id_24>",
|
| 629 |
-
"lstrip": true,
|
| 630 |
-
"normalized": false,
|
| 631 |
-
"rstrip": true,
|
| 632 |
-
"single_word": false,
|
| 633 |
-
"special": true
|
| 634 |
-
},
|
| 635 |
-
"104": {
|
| 636 |
-
"content": "<extra_id_23>",
|
| 637 |
-
"lstrip": true,
|
| 638 |
-
"normalized": false,
|
| 639 |
-
"rstrip": true,
|
| 640 |
-
"single_word": false,
|
| 641 |
-
"special": true
|
| 642 |
-
},
|
| 643 |
-
"105": {
|
| 644 |
-
"content": "<extra_id_22>",
|
| 645 |
-
"lstrip": true,
|
| 646 |
-
"normalized": false,
|
| 647 |
-
"rstrip": true,
|
| 648 |
-
"single_word": false,
|
| 649 |
-
"special": true
|
| 650 |
-
},
|
| 651 |
-
"106": {
|
| 652 |
-
"content": "<extra_id_21>",
|
| 653 |
-
"lstrip": true,
|
| 654 |
-
"normalized": false,
|
| 655 |
-
"rstrip": true,
|
| 656 |
-
"single_word": false,
|
| 657 |
-
"special": true
|
| 658 |
-
},
|
| 659 |
-
"107": {
|
| 660 |
-
"content": "<extra_id_20>",
|
| 661 |
-
"lstrip": true,
|
| 662 |
-
"normalized": false,
|
| 663 |
-
"rstrip": true,
|
| 664 |
-
"single_word": false,
|
| 665 |
-
"special": true
|
| 666 |
-
},
|
| 667 |
-
"108": {
|
| 668 |
-
"content": "<extra_id_19>",
|
| 669 |
-
"lstrip": true,
|
| 670 |
-
"normalized": false,
|
| 671 |
-
"rstrip": true,
|
| 672 |
-
"single_word": false,
|
| 673 |
-
"special": true
|
| 674 |
-
},
|
| 675 |
-
"109": {
|
| 676 |
-
"content": "<extra_id_18>",
|
| 677 |
-
"lstrip": true,
|
| 678 |
-
"normalized": false,
|
| 679 |
-
"rstrip": true,
|
| 680 |
-
"single_word": false,
|
| 681 |
-
"special": true
|
| 682 |
-
},
|
| 683 |
-
"110": {
|
| 684 |
-
"content": "<extra_id_17>",
|
| 685 |
-
"lstrip": true,
|
| 686 |
-
"normalized": false,
|
| 687 |
-
"rstrip": true,
|
| 688 |
-
"single_word": false,
|
| 689 |
-
"special": true
|
| 690 |
-
},
|
| 691 |
-
"111": {
|
| 692 |
-
"content": "<extra_id_16>",
|
| 693 |
-
"lstrip": true,
|
| 694 |
-
"normalized": false,
|
| 695 |
-
"rstrip": true,
|
| 696 |
-
"single_word": false,
|
| 697 |
-
"special": true
|
| 698 |
-
},
|
| 699 |
-
"112": {
|
| 700 |
-
"content": "<extra_id_15>",
|
| 701 |
-
"lstrip": true,
|
| 702 |
-
"normalized": false,
|
| 703 |
-
"rstrip": true,
|
| 704 |
-
"single_word": false,
|
| 705 |
-
"special": true
|
| 706 |
-
},
|
| 707 |
-
"113": {
|
| 708 |
-
"content": "<extra_id_14>",
|
| 709 |
-
"lstrip": true,
|
| 710 |
-
"normalized": false,
|
| 711 |
-
"rstrip": true,
|
| 712 |
-
"single_word": false,
|
| 713 |
-
"special": true
|
| 714 |
-
},
|
| 715 |
-
"114": {
|
| 716 |
-
"content": "<extra_id_13>",
|
| 717 |
-
"lstrip": true,
|
| 718 |
-
"normalized": false,
|
| 719 |
-
"rstrip": true,
|
| 720 |
-
"single_word": false,
|
| 721 |
-
"special": true
|
| 722 |
-
},
|
| 723 |
-
"115": {
|
| 724 |
-
"content": "<extra_id_12>",
|
| 725 |
-
"lstrip": true,
|
| 726 |
-
"normalized": false,
|
| 727 |
-
"rstrip": true,
|
| 728 |
-
"single_word": false,
|
| 729 |
-
"special": true
|
| 730 |
-
},
|
| 731 |
-
"116": {
|
| 732 |
-
"content": "<extra_id_11>",
|
| 733 |
-
"lstrip": true,
|
| 734 |
-
"normalized": false,
|
| 735 |
-
"rstrip": true,
|
| 736 |
-
"single_word": false,
|
| 737 |
-
"special": true
|
| 738 |
-
},
|
| 739 |
-
"117": {
|
| 740 |
-
"content": "<extra_id_10>",
|
| 741 |
-
"lstrip": true,
|
| 742 |
-
"normalized": false,
|
| 743 |
-
"rstrip": true,
|
| 744 |
-
"single_word": false,
|
| 745 |
-
"special": true
|
| 746 |
-
},
|
| 747 |
-
"118": {
|
| 748 |
-
"content": "<extra_id_9>",
|
| 749 |
-
"lstrip": true,
|
| 750 |
-
"normalized": false,
|
| 751 |
-
"rstrip": true,
|
| 752 |
-
"single_word": false,
|
| 753 |
-
"special": true
|
| 754 |
-
},
|
| 755 |
-
"119": {
|
| 756 |
-
"content": "<extra_id_8>",
|
| 757 |
-
"lstrip": true,
|
| 758 |
-
"normalized": false,
|
| 759 |
-
"rstrip": true,
|
| 760 |
-
"single_word": false,
|
| 761 |
-
"special": true
|
| 762 |
-
},
|
| 763 |
-
"120": {
|
| 764 |
-
"content": "<extra_id_7>",
|
| 765 |
-
"lstrip": true,
|
| 766 |
-
"normalized": false,
|
| 767 |
-
"rstrip": true,
|
| 768 |
-
"single_word": false,
|
| 769 |
-
"special": true
|
| 770 |
-
},
|
| 771 |
-
"121": {
|
| 772 |
-
"content": "<extra_id_6>",
|
| 773 |
-
"lstrip": true,
|
| 774 |
-
"normalized": false,
|
| 775 |
-
"rstrip": true,
|
| 776 |
-
"single_word": false,
|
| 777 |
-
"special": true
|
| 778 |
-
},
|
| 779 |
-
"122": {
|
| 780 |
-
"content": "<extra_id_5>",
|
| 781 |
-
"lstrip": true,
|
| 782 |
-
"normalized": false,
|
| 783 |
-
"rstrip": true,
|
| 784 |
-
"single_word": false,
|
| 785 |
-
"special": true
|
| 786 |
-
},
|
| 787 |
-
"123": {
|
| 788 |
-
"content": "<extra_id_4>",
|
| 789 |
-
"lstrip": true,
|
| 790 |
-
"normalized": false,
|
| 791 |
-
"rstrip": true,
|
| 792 |
-
"single_word": false,
|
| 793 |
-
"special": true
|
| 794 |
-
},
|
| 795 |
-
"124": {
|
| 796 |
-
"content": "<extra_id_3>",
|
| 797 |
-
"lstrip": true,
|
| 798 |
-
"normalized": false,
|
| 799 |
-
"rstrip": true,
|
| 800 |
-
"single_word": false,
|
| 801 |
-
"special": true
|
| 802 |
-
},
|
| 803 |
-
"125": {
|
| 804 |
-
"content": "<extra_id_2>",
|
| 805 |
-
"lstrip": true,
|
| 806 |
-
"normalized": false,
|
| 807 |
-
"rstrip": true,
|
| 808 |
-
"single_word": false,
|
| 809 |
-
"special": true
|
| 810 |
-
},
|
| 811 |
-
"126": {
|
| 812 |
-
"content": "<extra_id_1>",
|
| 813 |
-
"lstrip": true,
|
| 814 |
-
"normalized": false,
|
| 815 |
-
"rstrip": true,
|
| 816 |
-
"single_word": false,
|
| 817 |
-
"special": true
|
| 818 |
-
},
|
| 819 |
-
"127": {
|
| 820 |
-
"content": "<extra_id_0>",
|
| 821 |
-
"lstrip": true,
|
| 822 |
-
"normalized": false,
|
| 823 |
-
"rstrip": true,
|
| 824 |
-
"single_word": false,
|
| 825 |
-
"special": true
|
| 826 |
-
}
|
| 827 |
-
},
|
| 828 |
"additional_special_tokens": [
|
| 829 |
"<extra_id_0>",
|
| 830 |
"<extra_id_1>",
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"additional_special_tokens": [
|
| 3 |
"<extra_id_0>",
|
| 4 |
"<extra_id_1>",
|