| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[PAD]", | |
| "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": "[META]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 412, | |
| "content": "[SEN_100]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 413, | |
| "content": "[SEN_99]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 414, | |
| "content": "[SEN_98]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 415, | |
| "content": "[SEN_97]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 416, | |
| "content": "[SEN_96]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 417, | |
| "content": "[SEN_95]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 418, | |
| "content": "[SEN_94]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 419, | |
| "content": "[SEN_93]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 420, | |
| "content": "[SEN_92]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 421, | |
| "content": "[SEN_91]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 422, | |
| "content": "[SEN_90]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 423, | |
| "content": "[SEN_89]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 424, | |
| "content": "[SEN_88]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 425, | |
| "content": "[SEN_87]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 426, | |
| "content": "[SEN_86]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 427, | |
| "content": "[SEN_85]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 428, | |
| "content": "[SEN_84]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 429, | |
| "content": "[SEN_83]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 430, | |
| "content": "[SEN_82]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 431, | |
| "content": "[SEN_81]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 432, | |
| "content": "[SEN_80]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 433, | |
| "content": "[SEN_79]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 434, | |
| "content": "[SEN_78]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 435, | |
| "content": "[SEN_77]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 436, | |
| "content": "[SEN_76]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 437, | |
| "content": "[SEN_75]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 438, | |
| "content": "[SEN_74]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 439, | |
| "content": "[SEN_73]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 440, | |
| "content": "[SEN_72]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 441, | |
| "content": "[SEN_71]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 442, | |
| "content": "[SEN_70]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 443, | |
| "content": "[SEN_69]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 444, | |
| "content": "[SEN_68]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 445, | |
| "content": "[SEN_67]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 446, | |
| "content": "[SEN_66]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 447, | |
| "content": "[SEN_65]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 448, | |
| "content": "[SEN_64]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 449, | |
| "content": "[SEN_63]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 450, | |
| "content": "[SEN_62]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 451, | |
| "content": "[SEN_61]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 452, | |
| "content": "[SEN_60]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 453, | |
| "content": "[SEN_59]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 454, | |
| "content": "[SEN_58]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 455, | |
| "content": "[SEN_57]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 456, | |
| "content": "[SEN_56]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 457, | |
| "content": "[SEN_55]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 458, | |
| "content": "[SEN_54]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 459, | |
| "content": "[SEN_53]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 460, | |
| "content": "[SEN_52]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 461, | |
| "content": "[SEN_51]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 462, | |
| "content": "[SEN_50]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 463, | |
| "content": "[SEN_49]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 464, | |
| "content": "[SEN_48]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 465, | |
| "content": "[SEN_47]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 466, | |
| "content": "[SEN_46]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 467, | |
| "content": "[SEN_45]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 468, | |
| "content": "[SEN_44]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 469, | |
| "content": "[SEN_43]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 470, | |
| "content": "[SEN_42]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 471, | |
| "content": "[SEN_41]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 472, | |
| "content": "[SEN_40]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 473, | |
| "content": "[SEN_39]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 474, | |
| "content": "[SEN_38]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 475, | |
| "content": "[SEN_37]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 476, | |
| "content": "[SEN_36]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 477, | |
| "content": "[SEN_35]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 478, | |
| "content": "[SEN_34]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 479, | |
| "content": "[SEN_33]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 480, | |
| "content": "[SEN_32]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 481, | |
| "content": "[SEN_31]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 482, | |
| "content": "[SEN_30]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 483, | |
| "content": "[SEN_29]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 484, | |
| "content": "[SEN_28]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 485, | |
| "content": "[SEN_27]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 486, | |
| "content": "[SEN_26]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 487, | |
| "content": "[SEN_25]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 488, | |
| "content": "[SEN_24]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 489, | |
| "content": "[SEN_23]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 490, | |
| "content": "[SEN_22]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 491, | |
| "content": "[SEN_21]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 492, | |
| "content": "[SEN_20]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 493, | |
| "content": "[SEN_19]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 494, | |
| "content": "[SEN_18]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 495, | |
| "content": "[SEN_17]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 496, | |
| "content": "[SEN_16]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 497, | |
| "content": "[SEN_15]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 498, | |
| "content": "[SEN_14]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 499, | |
| "content": "[SEN_13]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 500, | |
| "content": "[SEN_12]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 501, | |
| "content": "[SEN_11]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 502, | |
| "content": "[SEN_10]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 503, | |
| "content": "[SEN_9]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 504, | |
| "content": "[SEN_8]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 505, | |
| "content": "[SEN_7]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 506, | |
| "content": "[SEN_6]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 507, | |
| "content": "[SEN_5]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 508, | |
| "content": "[SEN_4]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 509, | |
| "content": "[SEN_3]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 510, | |
| "content": "[SEN_2]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 511, | |
| "content": "[SEN_1]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "String": "" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[SEP]", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[SEP]", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[SEP]", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "[SEP]": { | |
| "id": "[SEP]", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "[SEP]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": { | |
| "type": "WordPiece", | |
| "prefix": "", | |
| "cleanup": true | |
| }, | |
| "model": { | |
| "type": "WordPiece", | |
| "unk_token": "[UNK]", | |
| "continuing_subword_prefix": "", | |
| "max_input_chars_per_word": 999999999, | |
| "vocab": { | |
| "[UNK]": 0, | |
| "[PAD]": 1, | |
| "[CLS]": 2, | |
| "[SEP]": 3, | |
| "[META]": 4, | |
| " ": 5, | |
| "а": 6, | |
| "и": 7, | |
| "е": 8, | |
| "о": 9, | |
| "т": 10, | |
| "н": 11, | |
| "р": 12, | |
| "с": 13, | |
| "в": 14, | |
| "л": 15, | |
| "д": 16, | |
| "к": 17, | |
| "п": 18, | |
| "м": 19, | |
| "з": 20, | |
| "я": 21, | |
| "ъ": 22, | |
| ",": 23, | |
| "б": 24, | |
| ".": 25, | |
| "г": 26, | |
| "у": 27, | |
| "ч": 28, | |
| "ж": 29, | |
| "ц": 30, | |
| "\n": 31, | |
| "щ": 32, | |
| "й": 33, | |
| "х": 34, | |
| "ш": 35, | |
| "0": 36, | |
| "-": 37, | |
| "1": 38, | |
| "ф": 39, | |
| "\"": 40, | |
| "2": 41, | |
| "С": 42, | |
| "П": 43, | |
| "e": 44, | |
| "Н": 45, | |
| "В": 46, | |
| "Т": 47, | |
| "a": 48, | |
| "А": 49, | |
| "К": 50, | |
| "o": 51, | |
| ":": 52, | |
| "i": 53, | |
| "И": 54, | |
| "Б": 55, | |
| "Д": 56, | |
| "О": 57, | |
| "t": 58, | |
| "М": 59, | |
| "n": 60, | |
| "r": 61, | |
| "Р": 62, | |
| "3": 63, | |
| "ю": 64, | |
| "5": 65, | |
| "Е": 66, | |
| "s": 67, | |
| "4": 68, | |
| "l": 69, | |
| "9": 70, | |
| "З": 71, | |
| ")": 72, | |
| "8": 73, | |
| "(": 74, | |
| "6": 75, | |
| "7": 76, | |
| "Г": 77, | |
| "c": 78, | |
| "Л": 79, | |
| "m": 80, | |
| "–": 81, | |
| "d": 82, | |
| "u": 83, | |
| "/": 84, | |
| "h": 85, | |
| "?": 86, | |
| "g": 87, | |
| "!": 88, | |
| "p": 89, | |
| "b": 90, | |
| "Х": 91, | |
| "S": 92, | |
| "—": 93, | |
| "У": 94, | |
| "A": 95, | |
| ";": 96, | |
| "Ф": 97, | |
| "I": 98, | |
| "y": 99, | |
| "C": 100, | |
| "k": 101, | |
| "Ч": 102, | |
| "v": 103, | |
| "w": 104, | |
| "P": 105, | |
| "T": 106, | |
| "Ц": 107, | |
| "B": 108, | |
| "D": 109, | |
| "M": 110, | |
| "f": 111, | |
| "„": 112, | |
| "E": 113, | |
| "%": 114, | |
| "R": 115, | |
| "ь": 116, | |
| "“": 117, | |
| "N": 118, | |
| "L": 119, | |
| "G": 120, | |
| "O": 121, | |
| "Щ": 122, | |
| "V": 123, | |
| "F": 124, | |
| "Я": 125, | |
| "|": 126, | |
| "Ш": 127, | |
| "H": 128, | |
| "Ж": 129, | |
| "…": 130, | |
| "W": 131, | |
| "z": 132, | |
| "x": 133, | |
| "”": 134, | |
| "Й": 135, | |
| "U": 136, | |
| "]": 137, | |
| "[": 138, | |
| "Ю": 139, | |
| "'": 140, | |
| "*": 141, | |
| "K": 142, | |
| "#": 143, | |
| "Ъ": 144, | |
| "X": 145, | |
| "»": 146, | |
| "+": 147, | |
| "J": 148, | |
| "_": 149, | |
| "": 150, | |
| "•": 151, | |
| "q": 152, | |
| "№": 153, | |
| "j": 154, | |
| "Y": 155, | |
| "=": 156, | |
| "\t": 157, | |
| ">": 158, | |
| "Z": 159, | |
| "&": 160, | |
| "І": 161, | |
| "·": 162, | |
| "«": 163, | |
| "°": 164, | |
| "Q": 165, | |
| "$": 166, | |
| "@": 167, | |
| "ѣ": 168, | |
| "ы": 169, | |
| "<": 170, | |
| "": 171, | |
| " ": 172, | |
| "ĸ": 173, | |
| "}": 174, | |
| "{": 175, | |
| "↑": 176, | |
| "©": 177, | |
| "§": 178, | |
| "®": 179, | |
| "é": 180, | |
| "\\": 181, | |
| "›": 182, | |
| "→": 183, | |
| "’": 184, | |
| "�": 185, | |
| "α": 186, | |
| "€": 187, | |
| "ο": 188, | |
| "~": 189, | |
| "🙂": 190, | |
| "ѫ": 191, | |
| "`": 192, | |
| "ν": 193, | |
| "ü": 194, | |
| "ι": 195, | |
| "τ": 196, | |
| "►": 197, | |
| "″": 198, | |
| "ς": 199, | |
| "ρ": 200, | |
| "э": 201, | |
| "ε": 202, | |
| "ä": 203, | |
| "κ": 204, | |
| "σ": 205, | |
| "λ": 206, | |
| "⋅": 207, | |
| "™": 208, | |
| "²": 209, | |
| "ö": 210, | |
| "μ": 211, | |
| "á": 212, | |
| "️": 213, | |
| "←": 214, | |
| "†": 215, | |
| "Ь": 216, | |
| "ј": 217, | |
| "і": 218, | |
| "η": 219, | |
| "×": 220, | |
| "′": 221, | |
| "è": 222, | |
| "¬": 223, | |
| "υ": 224, | |
| "à": 225, | |
| "^": 226, | |
| "ó": 227, | |
| "π": 228, | |
| "í": 229, | |
| "ί": 230, | |
| "": 231, | |
| "Π": 232, | |
| "ا": 233, | |
| "£": 234, | |
| "ά": 235, | |
| "ı": 236, | |
| "●": 237, | |
| "★": 238, | |
| "½": 239, | |
| "γ": 240, | |
| "‑": 241, | |
| "ç": 242, | |
| "‘": 243, | |
| "ω": 244, | |
| "ό": 245, | |
| "ل": 246, | |
| "😉": 247, | |
| "δ": 248, | |
| "Э": 249, | |
| "✔": 250, | |
| "😀": 251, | |
| "♥": 252, | |
| "Δ": 253, | |
| "š": 254, | |
| "😂": 255, | |
| "ñ": 256, | |
| "❤": 257, | |
| "є": 258, | |
| "β": 259, | |
| "č": 260, | |
| "−": 261, | |
| "ł": 262, | |
| "ή": 263, | |
| "́": 264, | |
| "Ε": 265, | |
| "â": 266, | |
| "Α": 267, | |
| "έ": 268, | |
| "ر": 269, | |
| "º": 270, | |
| "ي": 271, | |
| "å": 272, | |
| "ò": 273, | |
| "±": 274, | |
| "Ø": 275, | |
| "ş": 276, | |
| "ú": 277, | |
| "ù": 278, | |
| "ß": 279, | |
| "µ": 280, | |
| "ă": 281, | |
| "ê": 282, | |
| "【": 283, | |
| "】": 284, | |
| "ë": 285, | |
| "م": 286, | |
| "و": 287, | |
| "ё": 288, | |
| "θ": 289, | |
| "ύ": 290, | |
| "χ": 291, | |
| "⇒": 292, | |
| "✓": 293, | |
| "ô": 294, | |
| "♦": 295, | |
| "ć": 296, | |
| " ": 297, | |
| "î": 298, | |
| "Ü": 299, | |
| "": 300, | |
| "¼": 301, | |
| "Σ": 302, | |
| "Μ": 303, | |
| "φ": 304, | |
| "ї": 305, | |
| "Κ": 306, | |
| "É": 307, | |
| "ن": 308, | |
| "Ö": 309, | |
| "ώ": 310, | |
| "✅": 311, | |
| "̆": 312, | |
| "ø": 313, | |
| "♠": 314, | |
| "ب": 315, | |
| "ᐉ": 316, | |
| "Ι": 317, | |
| "Ο": 318, | |
| "ѕ": 319, | |
| "İ": 320, | |
| "њ": 321, | |
| "▼": 322, | |
| "Ѕ": 323, | |
| "ت": 324, | |
| "ž": 325, | |
| "ћ": 326, | |
| "↓": 327, | |
| "ع": 328, | |
| "Č": 329, | |
| "ę": 330, | |
| "😁": 331, | |
| "ā": 332, | |
| "د": 333, | |
| "³": 334, | |
| "Τ": 335, | |
| "Β": 336, | |
| "🔘": 337, | |
| "َ": 338, | |
| "ğ": 339, | |
| "▷": 340, | |
| "📕": 341, | |
| "ة": 342, | |
| "℃": 343, | |
| "س": 344, | |
| "‹": 345, | |
| "Ν": 346, | |
| "‒": 347, | |
| "‰": 348, | |
| "": 349, | |
| "➡": 350, | |
| "æ": 351, | |
| "Š": 352, | |
| "☆": 353, | |
| "÷": 354, | |
| "י": 355, | |
| "😊": 356, | |
| "🤣": 357, | |
| "ã": 358, | |
| "ف": 359, | |
| "ه": 360, | |
| "Γ": 361, | |
| "ð": 362, | |
| "➤": 363, | |
| "■": 364, | |
| "≥": 365, | |
| "": 366, | |
| "Θ": 367, | |
| "Ј": 368, | |
| "ý": 369, | |
| "": 370, | |
| "中": 371, | |
| "⋆": 372, | |
| "▪": 373, | |
| "⭐": 374, | |
| "̣": 375, | |
| "¾": 376, | |
| "文": 377, | |
| "": 378, | |
| "―": 379, | |
| "ï": 380, | |
| "ζ": 381, | |
| "Ş": 382, | |
| "ì": 383, | |
| "Η": 384, | |
| "љ": 385, | |
| "》": 386, | |
| "≤": 387, | |
| "─": 388, | |
| "ξ": 389, | |
| " ": 390, | |
| "ی": 391, | |
| "☎": 392, | |
| "ś": 393, | |
| "̄": 394, | |
| "": 395, | |
| "Ы": 396, | |
| "า": 397, | |
| "⠀": 398, | |
| "∞": 399, | |
| "Λ": 400, | |
| "ě": 401, | |
| "¹": 402, | |
| "◊": 403, | |
| "ą": 404, | |
| "《": 405, | |
| "Á": 406, | |
| "ك": 407, | |
| "‐": 408, | |
| "👉": 409, | |
| "ق": 410, | |
| "Ç": 411, | |
| "[SEN_100]": 412, | |
| "[SEN_99]": 413, | |
| "[SEN_98]": 414, | |
| "[SEN_97]": 415, | |
| "[SEN_96]": 416, | |
| "[SEN_95]": 417, | |
| "[SEN_94]": 418, | |
| "[SEN_93]": 419, | |
| "[SEN_92]": 420, | |
| "[SEN_91]": 421, | |
| "[SEN_90]": 422, | |
| "[SEN_89]": 423, | |
| "[SEN_88]": 424, | |
| "[SEN_87]": 425, | |
| "[SEN_86]": 426, | |
| "[SEN_85]": 427, | |
| "[SEN_84]": 428, | |
| "[SEN_83]": 429, | |
| "[SEN_82]": 430, | |
| "[SEN_81]": 431, | |
| "[SEN_80]": 432, | |
| "[SEN_79]": 433, | |
| "[SEN_78]": 434, | |
| "[SEN_77]": 435, | |
| "[SEN_76]": 436, | |
| "[SEN_75]": 437, | |
| "[SEN_74]": 438, | |
| "[SEN_73]": 439, | |
| "[SEN_72]": 440, | |
| "[SEN_71]": 441, | |
| "[SEN_70]": 442, | |
| "[SEN_69]": 443, | |
| "[SEN_68]": 444, | |
| "[SEN_67]": 445, | |
| "[SEN_66]": 446, | |
| "[SEN_65]": 447, | |
| "[SEN_64]": 448, | |
| "[SEN_63]": 449, | |
| "[SEN_62]": 450, | |
| "[SEN_61]": 451, | |
| "[SEN_60]": 452, | |
| "[SEN_59]": 453, | |
| "[SEN_58]": 454, | |
| "[SEN_57]": 455, | |
| "[SEN_56]": 456, | |
| "[SEN_55]": 457, | |
| "[SEN_54]": 458, | |
| "[SEN_53]": 459, | |
| "[SEN_52]": 460, | |
| "[SEN_51]": 461, | |
| "[SEN_50]": 462, | |
| "[SEN_49]": 463, | |
| "[SEN_48]": 464, | |
| "[SEN_47]": 465, | |
| "[SEN_46]": 466, | |
| "[SEN_45]": 467, | |
| "[SEN_44]": 468, | |
| "[SEN_43]": 469, | |
| "[SEN_42]": 470, | |
| "[SEN_41]": 471, | |
| "[SEN_40]": 472, | |
| "[SEN_39]": 473, | |
| "[SEN_38]": 474, | |
| "[SEN_37]": 475, | |
| "[SEN_36]": 476, | |
| "[SEN_35]": 477, | |
| "[SEN_34]": 478, | |
| "[SEN_33]": 479, | |
| "[SEN_32]": 480, | |
| "[SEN_31]": 481, | |
| "[SEN_30]": 482, | |
| "[SEN_29]": 483, | |
| "[SEN_28]": 484, | |
| "[SEN_27]": 485, | |
| "[SEN_26]": 486, | |
| "[SEN_25]": 487, | |
| "[SEN_24]": 488, | |
| "[SEN_23]": 489, | |
| "[SEN_22]": 490, | |
| "[SEN_21]": 491, | |
| "[SEN_20]": 492, | |
| "[SEN_19]": 493, | |
| "[SEN_18]": 494, | |
| "[SEN_17]": 495, | |
| "[SEN_16]": 496, | |
| "[SEN_15]": 497, | |
| "[SEN_14]": 498, | |
| "[SEN_13]": 499, | |
| "[SEN_12]": 500, | |
| "[SEN_11]": 501, | |
| "[SEN_10]": 502, | |
| "[SEN_9]": 503, | |
| "[SEN_8]": 504, | |
| "[SEN_7]": 505, | |
| "[SEN_6]": 506, | |
| "[SEN_5]": 507, | |
| "[SEN_4]": 508, | |
| "[SEN_3]": 509, | |
| "[SEN_2]": 510, | |
| "[SEN_1]": 511 | |
| } | |
| } | |
| } |