{ "version": "1.0", "truncation": { "direction": "Right", "max_length": 32, "strategy": "LongestFirst", "stride": 0 }, "padding": { "strategy": { "Fixed": 32 }, "direction": "Right", "pad_to_multiple_of": null, "pad_id": 0, "pad_type_id": 0, "pad_token": "[PAD]" }, "added_tokens": [ { "id": 0, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "WhitespaceSplit" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": { "[CLS]": { "id": "[CLS]", "ids": [ 2 ], "tokens": [ "[CLS]" ] }, "[SEP]": { "id": "[SEP]", "ids": [ 3 ], "tokens": [ "[SEP]" ] } } }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "[PAD]": 0, "[UNK]": 1, "[CLS]": 2, "[SEP]": 3, "[MASK]": 4, "T99": 5, "T100": 6, "T101": 7, "T102": 8, "T103": 9, "T104": 10, "T105": 11, "T106": 12, "T107": 13, "T108": 14, "T109": 15, "T110": 16, "T111": 17, "T112": 18, "T113": 19, "T114": 20, "T116": 21, "T117": 22, "T118": 23, "T119": 24, "T120": 25, "T121": 26, "T122": 27, "T123": 28, "T124": 29, "T125": 30, "T126": 31, "T129": 32, "T130": 33, "T133": 34, "T134": 35, "T136": 36, "T137": 37, "T138": 38, "T139": 39, "T140": 40, "T141": 41, "T142": 42, "T143": 43, "T144": 44, "T145": 45, "T146": 46, "T147": 47, "T148": 48, "T149": 49, "T150": 50, "T151": 51, "T152": 52, "T154": 53, "T155": 54, "T156": 55, "T157": 56, "T158": 57, "T159": 58, "T162": 59, "T163": 60, "T164": 61, "T165": 62, "T167": 63, "T168": 64, "T169": 65, "T170": 66, "T171": 67, "T172": 68, "T173": 69, "T174": 70, "T175": 71, "T176": 72, "T177": 73, "T178": 74, "T179": 75, "T180": 76, "T181": 77, "T182": 78, "T183": 79, "T184": 80, "T186": 81, "T187": 82, "T190": 83, "T191": 84, "T192": 85, "T193": 86, "T194": 87, "T195": 88, "T196": 89, "T197": 90, "T198": 91, "T199": 92, "T200": 93, "T201": 94, "T202": 95, "T203": 96, "T204": 97, "T205": 98, "T206": 99, "T208": 100, "T209": 101, "T210": 102, "T211": 103, "T212": 104, "T213": 105, "T214": 106, "T215": 107, "T216": 108, "T217": 109, "T218": 110, "T221": 111, "T222": 112, "T223": 113, "T224": 114, "T225": 115, "T226": 116, "T227": 117, "T228": 118, "T229": 119, "T230": 120, "T231": 121, "T232": 122, "T233": 123, "T234": 124, "T235": 125, "T236": 126, "T238": 127, "T239": 128, "T240": 129, "T241": 130, "T242": 131, "T243": 132, "T244": 133, "T245": 134, "T246": 135, "T247": 136, "T248": 137, "T249": 138, "T250": 139, "T251": 140, "T252": 141, "T253": 142, "T254": 143, "T255": 144, "T256": 145, "T257": 146, "T258": 147, "T259": 148, "T261": 149, "T262": 150, "T263": 151, "T264": 152, "T265": 153, "T267": 154, "T268": 155, "T269": 156, "T270": 157, "T271": 158, "T272": 159, "T273": 160, "T274": 161, "T276": 162, "T277": 163, "T278": 164, "T279": 165, "T280": 166, "T281": 167, "T282": 168, "T283": 169, "T284": 170, "T286": 171, "T287": 172, "T288": 173, "T289": 174, "T290": 175, "T291": 176, "T292": 177, "T293": 178, "T294": 179, "T295": 180, "T296": 181, "T297": 182, "T298": 183, "T299": 184, "T300": 185, "T301": 186, "T302": 187, "T304": 188, "T305": 189, "T306": 190, "T307": 191, "T308": 192, "T310": 193, "T312": 194, "T313": 195, "T314": 196, "T315": 197, "T316": 198, "T317": 199, "T318": 200, "T319": 201, "T320": 202, "T321": 203, "T322": 204, "T323": 205, "T324": 206, "T325": 207, "T326": 208, "T327": 209, "T328": 210, "T329": 211, "T330": 212, "T331": 213, "T332": 214, "T333": 215, "T335": 216, "T336": 217, "T337": 218, "T338": 219, "T339": 220, "T340": 221, "T341": 222, "T342": 223, "T343": 224, "T344": 225, "T345": 226, "T346": 227, "T347": 228, "T348": 229, "T349": 230, "T350": 231, "T351": 232, "T352": 233, "T353": 234, "T354": 235, "T355": 236, "T356": 237, "T357": 238, "T358": 239, "T359": 240, "T360": 241, "T361": 242, "T362": 243, "T363": 244, "T365": 245, "T366": 246, "T367": 247, "T368": 248, "T369": 249, "T370": 250, "T372": 251, "T373": 252, "T374": 253, "T375": 254, "T376": 255, "T377": 256, "T378": 257, "T379": 258, "T380": 259, "T381": 260, "T382": 261, "T383": 262, "T384": 263, "T385": 264, "T386": 265, "T387": 266, "T388": 267, "T389": 268, "T390": 269, "T391": 270, "T392": 271, "T393": 272, "T394": 273, "T395": 274, "T396": 275, "T397": 276, "T399": 277, "T400": 278, "T401": 279, "T402": 280, "T403": 281, "T404": 282, "T405": 283, "T406": 284, "T407": 285, "T408": 286, "T409": 287, "T411": 288, "T412": 289, "T413": 290, "T414": 291, "T415": 292, "T416": 293, "T417": 294, "T418": 295, "T419": 296, "T420": 297, "T421": 298, "T422": 299, "T424": 300, "T425": 301, "T426": 302, "T427": 303, "T428": 304, "T430": 305, "T431": 306, "T432": 307, "T433": 308, "T434": 309, "T435": 310, "T436": 311, "T437": 312, "T438": 313, "T439": 314, "T440": 315, "T441": 316, "T442": 317, "T443": 318, "T444": 319, "T445": 320, "T446": 321, "T448": 322, "T449": 323, "T450": 324, "T451": 325, "T452": 326, "T453": 327, "T455": 328, "T456": 329, "T457": 330, "T458": 331, "T459": 332, "T460": 333, "T461": 334, "T462": 335, "T463": 336, "T464": 337, "T465": 338, "T466": 339, "T467": 340, "T468": 341, "T469": 342, "T470": 343, "T471": 344, "T472": 345, "T473": 346, "T474": 347, "T475": 348, "T476": 349, "T477": 350, "T478": 351, "T479": 352, "T480": 353, "T481": 354, "T482": 355, "T483": 356, "T484": 357, "T485": 358, "T486": 359, "T487": 360, "T489": 361, "T490": 362, "T491": 363, "T492": 364, "T494": 365, "T495": 366, "T496": 367, "T497": 368, "T498": 369, "T499": 370, "T500": 371, "T501": 372, "T502": 373, "T503": 374, "T505": 375, "T506": 376, "T507": 377, "T508": 378, "T509": 379, "T510": 380, "T511": 381, "T512": 382, "T513": 383, "T514": 384, "T515": 385, "T516": 386, "T517": 387, "T518": 388, "T519": 389, "T520": 390, "T521": 391, "T522": 392, "T523": 393, "T525": 394, "T526": 395, "T527": 396, "T528": 397, "T529": 398, "T530": 399, "T531": 400, "T532": 401, "T533": 402, "T534": 403, "T535": 404, "T536": 405, "T537": 406, "T538": 407, "T539": 408, "T541": 409, "T543": 410, "T544": 411, "T545": 412, "T546": 413, "T547": 414, "T548": 415, "T550": 416, "T551": 417, "T552": 418, "T553": 419, "T554": 420, "T555": 421, "T556": 422, "T558": 423, "T559": 424, "T560": 425, "T561": 426, "T563": 427, "T564": 428, "T565": 429, "T566": 430, "T567": 431, "T568": 432, "T569": 433, "T570": 434, "T571": 435, "T572": 436, "T573": 437, "T574": 438, "T575": 439, "T577": 440, "T578": 441, "T579": 442, "T580": 443, "T581": 444, "T582": 445, "T583": 446, "T584": 447, "T585": 448, "T586": 449, "T587": 450, "T588": 451, "T589": 452, "T590": 453, "T591": 454, "T592": 455, "T593": 456, "T594": 457, "T595": 458, "T596": 459, "T597": 460, "T598": 461, "T599": 462, "T600": 463, "T601": 464, "T602": 465, "T604": 466, "T606": 467, "T607": 468, "T608": 469, "T609": 470, "T610": 471, "T611": 472, "T614": 473, "T615": 474, "T616": 475, "T617": 476, "T618": 477, "T620": 478, "T621": 479, "T622": 480, "T624": 481, "T625": 482, "T626": 483, "T627": 484, "T629": 485, "T630": 486, "T631": 487, "T632": 488, "T633": 489, "T635": 490, "T637": 491, "T638": 492, "T639": 493, "T640": 494, "T641": 495, "T642": 496, "T643": 497, "T644": 498, "T645": 499, "T646": 500, "T647": 501, "T648": 502, "T649": 503, "T650": 504, "T652": 505, "T653": 506, "T654": 507, "T655": 508, "T657": 509, "T658": 510, "T660": 511, "T661": 512, "T662": 513, "T663": 514, "T664": 515, "T665": 516, "T666": 517, "T667": 518, "T668": 519, "T672": 520, "T674": 521, "T675": 522, "T676": 523, "T677": 524, "T678": 525, "T679": 526, "T680": 527, "T681": 528, "T682": 529, "T683": 530, "T684": 531, "T685": 532, "T687": 533, "T688": 534, "T689": 535, "T690": 536, "T691": 537, "T692": 538, "T693": 539, "T694": 540, "T695": 541, "T696": 542, "T697": 543, "T698": 544, "T699": 545, "T701": 546, "T702": 547, "T703": 548, "T704": 549, "T705": 550, "T707": 551, "T708": 552, "T709": 553, "T710": 554, "T711": 555, "T712": 556, "T713": 557, "T714": 558, "T715": 559, "T716": 560, "T717": 561, "T719": 562, "T721": 563, "T723": 564, "T725": 565, "T726": 566, "T727": 567, "T728": 568, "T729": 569, "T730": 570, "T731": 571, "T732": 572, "T733": 573, "T734": 574, "T735": 575, "T736": 576, "T737": 577, "T738": 578, "T739": 579, "T741": 580, "T742": 581, "T743": 582, "T744": 583, "T745": 584, "T746": 585, "T747": 586, "T748": 587, "T749": 588, "T750": 589, "T751": 590, "T752": 591, "T753": 592, "T754": 593, "T755": 594, "T756": 595, "T757": 596, "T758": 597, "T759": 598, "T760": 599, "T761": 600, "T762": 601, "T763": 602, "T764": 603, "T765": 604, "T766": 605, "T767": 606, "T768": 607, "T769": 608, "T770": 609, "T771": 610, "T772": 611, "T773": 612, "T774": 613, "T775": 614, "T776": 615, "T777": 616, "T778": 617, "T779": 618, "T780": 619, "T781": 620, "T782": 621, "T783": 622, "T784": 623, "T785": 624, "T786": 625, "T787": 626, "T788": 627, "T789": 628, "T790": 629, "T792": 630, "T793": 631, "T794": 632, "T795": 633, "T797": 634, "T798": 635, "T799": 636, "T801": 637, "T803": 638, "T806": 639, "T807": 640, "T808": 641, "T809": 642, "T810": 643, "T811": 644, "T813": 645 }, "unk_token": "[UNK]" } }