hf-transformers-bot's picture
Add tiny processor fixture for testing
d65dd9c verified
Raw
History Blame Contribute Delete
16 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 100,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 101,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 102,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 103,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "BertNormalizer",
"clean_text": true,
"handle_chinese_chars": true,
"strip_accents": null,
"lowercase": true
},
"pre_tokenizer": {
"type": "BertPreTokenizer"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"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": {
"[CLS]": {
"id": "[CLS]",
"ids": [
101
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
102
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"model": {
"type": "WordPiece",
"unk_token": "[UNK]",
"continuing_subword_prefix": "##",
"max_input_chars_per_word": 100,
"vocab": {
"[PAD]": 0,
"[unused0]": 1,
"[unused1]": 2,
"[unused2]": 3,
"[unused3]": 4,
"[unused4]": 5,
"[unused5]": 6,
"[unused6]": 7,
"[unused7]": 8,
"[unused8]": 9,
"[unused9]": 10,
"[unused10]": 11,
"[unused11]": 12,
"[unused12]": 13,
"[unused13]": 14,
"[unused14]": 15,
"[unused15]": 16,
"[unused16]": 17,
"[unused17]": 18,
"[unused18]": 19,
"[unused19]": 20,
"[unused20]": 21,
"[unused21]": 22,
"[unused22]": 23,
"[unused23]": 24,
"[unused24]": 25,
"[unused25]": 26,
"[unused26]": 27,
"[unused27]": 28,
"[unused28]": 29,
"[unused29]": 30,
"[unused30]": 31,
"[unused31]": 32,
"[unused32]": 33,
"[unused33]": 34,
"[unused34]": 35,
"[unused35]": 36,
"[unused36]": 37,
"[unused37]": 38,
"[unused38]": 39,
"[unused39]": 40,
"[unused40]": 41,
"[unused41]": 42,
"[unused42]": 43,
"[unused43]": 44,
"[unused44]": 45,
"[unused45]": 46,
"[unused46]": 47,
"[unused47]": 48,
"[unused48]": 49,
"[unused49]": 50,
"[unused50]": 51,
"[unused51]": 52,
"[unused52]": 53,
"[unused53]": 54,
"[unused54]": 55,
"[unused55]": 56,
"[unused56]": 57,
"[unused57]": 58,
"[unused58]": 59,
"[unused59]": 60,
"[unused60]": 61,
"[unused61]": 62,
"[unused62]": 63,
"[unused63]": 64,
"[unused64]": 65,
"[unused65]": 66,
"[unused66]": 67,
"[unused67]": 68,
"[unused68]": 69,
"[unused69]": 70,
"[unused70]": 71,
"[unused71]": 72,
"[unused72]": 73,
"[unused73]": 74,
"[unused74]": 75,
"[unused75]": 76,
"[unused76]": 77,
"[unused77]": 78,
"[unused78]": 79,
"[unused79]": 80,
"[unused80]": 81,
"[unused81]": 82,
"[unused82]": 83,
"[unused83]": 84,
"[unused84]": 85,
"[unused85]": 86,
"[unused86]": 87,
"[unused87]": 88,
"[unused88]": 89,
"[unused89]": 90,
"[unused90]": 91,
"[unused91]": 92,
"[unused92]": 93,
"[unused93]": 94,
"[unused94]": 95,
"[unused95]": 96,
"[unused96]": 97,
"[unused97]": 98,
"[unused98]": 99,
"[UNK]": 100,
"[CLS]": 101,
"[SEP]": 102,
"[MASK]": 103,
"[unused99]": 104,
"[unused100]": 105,
"[unused101]": 106,
"[unused102]": 107,
"[unused103]": 108,
"[unused104]": 109,
"[unused105]": 110,
"[unused106]": 111,
"[unused107]": 112,
"[unused108]": 113,
"[unused109]": 114,
"[unused110]": 115,
"[unused111]": 116,
"[unused112]": 117,
"[unused113]": 118,
"[unused114]": 119,
"[unused115]": 120,
"[unused116]": 121,
"[unused117]": 122,
"[unused118]": 123,
"[unused119]": 124,
"[unused120]": 125,
"[unused121]": 126,
"[unused122]": 127,
"[unused123]": 128,
"[unused124]": 129,
"[unused125]": 130,
"[unused126]": 131,
"[unused127]": 132,
"[unused128]": 133,
"[unused129]": 134,
"[unused130]": 135,
"[unused131]": 136,
"[unused132]": 137,
"[unused133]": 138,
"[unused134]": 139,
"[unused135]": 140,
"[unused136]": 141,
"[unused137]": 142,
"[unused138]": 143,
"[unused139]": 144,
"[unused140]": 145,
"[unused141]": 146,
"[unused142]": 147,
"[unused143]": 148,
"[unused144]": 149,
"[unused145]": 150,
"[unused146]": 151,
"[unused147]": 152,
"[unused148]": 153,
"[unused149]": 154,
"[unused150]": 155,
"[unused151]": 156,
"[unused152]": 157,
"[unused153]": 158,
"[unused154]": 159,
"[unused155]": 160,
"[unused156]": 161,
"[unused157]": 162,
"[unused158]": 163,
"[unused159]": 164,
"[unused160]": 165,
"[unused161]": 166,
"[unused162]": 167,
"[unused163]": 168,
"[unused164]": 169,
"[unused165]": 170,
"[unused166]": 171,
"[unused167]": 172,
"[unused168]": 173,
"[unused169]": 174,
"[unused170]": 175,
"[unused171]": 176,
"[unused172]": 177,
"[unused173]": 178,
"[unused174]": 179,
"[unused175]": 180,
"[unused176]": 181,
"[unused177]": 182,
"[unused178]": 183,
"[unused179]": 184,
"[unused180]": 185,
"[unused181]": 186,
"[unused182]": 187,
"[unused183]": 188,
"[unused184]": 189,
"[unused185]": 190,
"[unused186]": 191,
"[unused187]": 192,
"[unused188]": 193,
"[unused189]": 194,
"[unused190]": 195,
"[unused191]": 196,
"[unused192]": 197,
"[unused193]": 198,
"[unused194]": 199,
"[unused195]": 200,
"[unused196]": 201,
"[unused197]": 202,
"[unused198]": 203,
"[unused199]": 204,
"[unused200]": 205,
"[unused201]": 206,
"[unused202]": 207,
"[unused203]": 208,
"[unused204]": 209,
"[unused205]": 210,
"[unused206]": 211,
"[unused207]": 212,
"[unused208]": 213,
"[unused209]": 214,
"[unused210]": 215,
"[unused211]": 216,
"[unused212]": 217,
"[unused213]": 218,
"[unused214]": 219,
"[unused215]": 220,
"[unused216]": 221,
"[unused217]": 222,
"[unused218]": 223,
"[unused219]": 224,
"[unused220]": 225,
"[unused221]": 226,
"[unused222]": 227,
"[unused223]": 228,
"[unused224]": 229,
"[unused225]": 230,
"[unused226]": 231,
"[unused227]": 232,
"[unused228]": 233,
"[unused229]": 234,
"[unused230]": 235,
"[unused231]": 236,
"[unused232]": 237,
"[unused233]": 238,
"[unused234]": 239,
"[unused235]": 240,
"[unused236]": 241,
"[unused237]": 242,
"[unused238]": 243,
"[unused239]": 244,
"[unused240]": 245,
"[unused241]": 246,
"[unused242]": 247,
"[unused243]": 248,
"[unused244]": 249,
"[unused245]": 250,
"[unused246]": 251,
"[unused247]": 252,
"[unused248]": 253,
"[unused249]": 254,
"[unused250]": 255,
"[unused251]": 256,
"[unused252]": 257,
"[unused253]": 258,
"[unused254]": 259,
"[unused255]": 260,
"[unused256]": 261,
"[unused257]": 262,
"[unused258]": 263,
"[unused259]": 264,
"[unused260]": 265,
"[unused261]": 266,
"[unused262]": 267,
"[unused263]": 268,
"[unused264]": 269,
"[unused265]": 270,
"[unused266]": 271,
"[unused267]": 272,
"[unused268]": 273,
"[unused269]": 274,
"[unused270]": 275,
"[unused271]": 276,
"[unused272]": 277,
"[unused273]": 278,
"[unused274]": 279,
"[unused275]": 280,
"[unused276]": 281,
"[unused277]": 282,
"[unused278]": 283,
"[unused279]": 284,
"[unused280]": 285,
"[unused281]": 286,
"[unused282]": 287,
"[unused283]": 288,
"[unused284]": 289,
"[unused285]": 290,
"[unused286]": 291,
"[unused287]": 292,
"[unused288]": 293,
"[unused289]": 294,
"[unused290]": 295,
"[unused291]": 296,
"[unused292]": 297,
"[unused293]": 298,
"[unused294]": 299,
"[unused295]": 300,
"[unused296]": 301,
"[unused297]": 302,
"[unused298]": 303,
"[unused299]": 304,
"[unused300]": 305,
"[unused301]": 306,
"[unused302]": 307,
"[unused303]": 308,
"[unused304]": 309,
"[unused305]": 310,
"[unused306]": 311,
"[unused307]": 312,
"[unused308]": 313,
"[unused309]": 314,
"[unused310]": 315,
"[unused311]": 316,
"[unused312]": 317,
"[unused313]": 318,
"[unused314]": 319,
"[unused315]": 320,
"[unused316]": 321,
"[unused317]": 322,
"[unused318]": 323,
"[unused319]": 324,
"[unused320]": 325,
"[unused321]": 326,
"[unused322]": 327,
"[unused323]": 328,
"[unused324]": 329,
"[unused325]": 330,
"[unused326]": 331,
"[unused327]": 332,
"[unused328]": 333,
"[unused329]": 334,
"[unused330]": 335,
"[unused331]": 336,
"[unused332]": 337,
"[unused333]": 338,
"[unused334]": 339,
"[unused335]": 340,
"[unused336]": 341,
"[unused337]": 342,
"[unused338]": 343,
"[unused339]": 344,
"[unused340]": 345,
"[unused341]": 346,
"[unused342]": 347,
"[unused343]": 348,
"[unused344]": 349,
"[unused345]": 350,
"[unused346]": 351,
"[unused347]": 352,
"[unused348]": 353,
"[unused349]": 354,
"[unused350]": 355,
"[unused351]": 356,
"[unused352]": 357,
"[unused353]": 358,
"[unused354]": 359,
"[unused355]": 360,
"[unused356]": 361,
"[unused357]": 362,
"[unused358]": 363,
"[unused359]": 364,
"[unused360]": 365,
"[unused361]": 366,
"[unused362]": 367,
"[unused363]": 368,
"[unused364]": 369,
"[unused365]": 370,
"[unused366]": 371,
"[unused367]": 372,
"[unused368]": 373,
"[unused369]": 374,
"[unused370]": 375,
"[unused371]": 376,
"[unused372]": 377,
"[unused373]": 378,
"[unused374]": 379,
"[unused375]": 380,
"[unused376]": 381,
"[unused377]": 382,
"[unused378]": 383,
"[unused379]": 384,
"[unused380]": 385,
"[unused381]": 386,
"[unused382]": 387,
"[unused383]": 388,
"[unused384]": 389,
"[unused385]": 390,
"[unused386]": 391,
"[unused387]": 392,
"[unused388]": 393,
"[unused389]": 394,
"[unused390]": 395,
"[unused391]": 396,
"[unused392]": 397,
"[unused393]": 398,
"[unused394]": 399,
"[unused395]": 400,
"[unused396]": 401,
"[unused397]": 402,
"[unused398]": 403,
"[unused399]": 404,
"[unused400]": 405,
"[unused401]": 406,
"[unused402]": 407,
"[unused403]": 408,
"[unused404]": 409,
"[unused405]": 410,
"[unused406]": 411,
"[unused407]": 412,
"[unused408]": 413,
"[unused409]": 414,
"[unused410]": 415,
"[unused411]": 416,
"[unused412]": 417,
"[unused413]": 418,
"[unused414]": 419,
"[unused415]": 420,
"[unused416]": 421,
"[unused417]": 422,
"[unused418]": 423,
"[unused419]": 424,
"[unused420]": 425,
"[unused421]": 426,
"[unused422]": 427,
"[unused423]": 428,
"[unused424]": 429,
"[unused425]": 430,
"[unused426]": 431,
"[unused427]": 432,
"[unused428]": 433,
"[unused429]": 434,
"[unused430]": 435,
"[unused431]": 436,
"[unused432]": 437,
"[unused433]": 438,
"[unused434]": 439,
"[unused435]": 440,
"[unused436]": 441,
"[unused437]": 442,
"[unused438]": 443,
"[unused439]": 444,
"[unused440]": 445,
"[unused441]": 446,
"[unused442]": 447,
"[unused443]": 448,
"[unused444]": 449,
"[unused445]": 450,
"[unused446]": 451,
"[unused447]": 452,
"[unused448]": 453,
"[unused449]": 454,
"[unused450]": 455,
"[unused451]": 456,
"[unused452]": 457,
"[unused453]": 458,
"[unused454]": 459,
"[unused455]": 460,
"[unused456]": 461,
"[unused457]": 462,
"[unused458]": 463,
"[unused459]": 464,
"[unused460]": 465,
"[unused461]": 466,
"[unused462]": 467,
"[unused463]": 468,
"[unused464]": 469,
"[unused465]": 470,
"[unused466]": 471,
"[unused467]": 472,
"[unused468]": 473,
"[unused469]": 474,
"[unused470]": 475,
"[unused471]": 476,
"[unused472]": 477,
"[unused473]": 478,
"[unused474]": 479,
"[unused475]": 480,
"[unused476]": 481,
"[unused477]": 482,
"[unused478]": 483,
"[unused479]": 484,
"[unused480]": 485,
"[unused481]": 486,
"[unused482]": 487,
"[unused483]": 488,
"[unused484]": 489,
"[unused485]": 490,
"[unused486]": 491,
"[unused487]": 492,
"[unused488]": 493,
"[unused489]": 494,
"[unused490]": 495,
"[unused491]": 496,
"[unused492]": 497,
"[unused493]": 498,
"[unused494]": 499
}
}
}