Upload processor

Browse files

Files changed (9) hide show

added_tokens.json +1027 -0
merges.txt +0 -0
preprocessor_config.json +28 -0
processing_travisionlm.py +276 -0
processor_config.json +6 -0
special_tokens_map.json +39 -0
tokenizer.json +0 -0
tokenizer_config.json +0 -0
vocab.json +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,1027 @@

+{
+  "<image>": 50257,
+  "<loc0000>": 50258,
+  "<loc0001>": 50259,
+  "<loc0002>": 50260,
+  "<loc0003>": 50261,
+  "<loc0004>": 50262,
+  "<loc0005>": 50263,
+  "<loc0006>": 50264,
+  "<loc0007>": 50265,
+  "<loc0008>": 50266,
+  "<loc0009>": 50267,
+  "<loc0010>": 50268,
+  "<loc0011>": 50269,
+  "<loc0012>": 50270,
+  "<loc0013>": 50271,
+  "<loc0014>": 50272,
+  "<loc0015>": 50273,
+  "<loc0016>": 50274,
+  "<loc0017>": 50275,
+  "<loc0018>": 50276,
+  "<loc0019>": 50277,
+  "<loc0020>": 50278,
+  "<loc0021>": 50279,
+  "<loc0022>": 50280,
+  "<loc0023>": 50281,
+  "<loc0024>": 50282,
+  "<loc0025>": 50283,
+  "<loc0026>": 50284,
+  "<loc0027>": 50285,
+  "<loc0028>": 50286,
+  "<loc0029>": 50287,
+  "<loc0030>": 50288,
+  "<loc0031>": 50289,
+  "<loc0032>": 50290,
+  "<loc0033>": 50291,
+  "<loc0034>": 50292,
+  "<loc0035>": 50293,
+  "<loc0036>": 50294,
+  "<loc0037>": 50295,
+  "<loc0038>": 50296,
+  "<loc0039>": 50297,
+  "<loc0040>": 50298,
+  "<loc0041>": 50299,
+  "<loc0042>": 50300,
+  "<loc0043>": 50301,
+  "<loc0044>": 50302,
+  "<loc0045>": 50303,
+  "<loc0046>": 50304,
+  "<loc0047>": 50305,
+  "<loc0048>": 50306,
+  "<loc0049>": 50307,
+  "<loc0050>": 50308,
+  "<loc0051>": 50309,
+  "<loc0052>": 50310,
+  "<loc0053>": 50311,
+  "<loc0054>": 50312,
+  "<loc0055>": 50313,
+  "<loc0056>": 50314,
+  "<loc0057>": 50315,
+  "<loc0058>": 50316,
+  "<loc0059>": 50317,
+  "<loc0060>": 50318,
+  "<loc0061>": 50319,
+  "<loc0062>": 50320,
+  "<loc0063>": 50321,
+  "<loc0064>": 50322,
+  "<loc0065>": 50323,
+  "<loc0066>": 50324,
+  "<loc0067>": 50325,
+  "<loc0068>": 50326,
+  "<loc0069>": 50327,
+  "<loc0070>": 50328,
+  "<loc0071>": 50329,
+  "<loc0072>": 50330,
+  "<loc0073>": 50331,
+  "<loc0074>": 50332,
+  "<loc0075>": 50333,
+  "<loc0076>": 50334,
+  "<loc0077>": 50335,
+  "<loc0078>": 50336,
+  "<loc0079>": 50337,
+  "<loc0080>": 50338,
+  "<loc0081>": 50339,
+  "<loc0082>": 50340,
+  "<loc0083>": 50341,
+  "<loc0084>": 50342,
+  "<loc0085>": 50343,
+  "<loc0086>": 50344,
+  "<loc0087>": 50345,
+  "<loc0088>": 50346,
+  "<loc0089>": 50347,
+  "<loc0090>": 50348,
+  "<loc0091>": 50349,
+  "<loc0092>": 50350,
+  "<loc0093>": 50351,
+  "<loc0094>": 50352,
+  "<loc0095>": 50353,
+  "<loc0096>": 50354,
+  "<loc0097>": 50355,
+  "<loc0098>": 50356,
+  "<loc0099>": 50357,
+  "<loc0100>": 50358,
+  "<loc0101>": 50359,
+  "<loc0102>": 50360,
+  "<loc0103>": 50361,
+  "<loc0104>": 50362,
+  "<loc0105>": 50363,
+  "<loc0106>": 50364,
+  "<loc0107>": 50365,
+  "<loc0108>": 50366,
+  "<loc0109>": 50367,
+  "<loc0110>": 50368,
+  "<loc0111>": 50369,
+  "<loc0112>": 50370,
+  "<loc0113>": 50371,
+  "<loc0114>": 50372,
+  "<loc0115>": 50373,
+  "<loc0116>": 50374,
+  "<loc0117>": 50375,
+  "<loc0118>": 50376,
+  "<loc0119>": 50377,
+  "<loc0120>": 50378,
+  "<loc0121>": 50379,
+  "<loc0122>": 50380,
+  "<loc0123>": 50381,
+  "<loc0124>": 50382,
+  "<loc0125>": 50383,
+  "<loc0126>": 50384,
+  "<loc0127>": 50385,
+  "<loc0128>": 50386,
+  "<loc0129>": 50387,
+  "<loc0130>": 50388,
+  "<loc0131>": 50389,
+  "<loc0132>": 50390,
+  "<loc0133>": 50391,
+  "<loc0134>": 50392,
+  "<loc0135>": 50393,
+  "<loc0136>": 50394,
+  "<loc0137>": 50395,
+  "<loc0138>": 50396,
+  "<loc0139>": 50397,
+  "<loc0140>": 50398,
+  "<loc0141>": 50399,
+  "<loc0142>": 50400,
+  "<loc0143>": 50401,
+  "<loc0144>": 50402,
+  "<loc0145>": 50403,
+  "<loc0146>": 50404,
+  "<loc0147>": 50405,
+  "<loc0148>": 50406,
+  "<loc0149>": 50407,
+  "<loc0150>": 50408,
+  "<loc0151>": 50409,
+  "<loc0152>": 50410,
+  "<loc0153>": 50411,
+  "<loc0154>": 50412,
+  "<loc0155>": 50413,
+  "<loc0156>": 50414,
+  "<loc0157>": 50415,
+  "<loc0158>": 50416,
+  "<loc0159>": 50417,
+  "<loc0160>": 50418,
+  "<loc0161>": 50419,
+  "<loc0162>": 50420,
+  "<loc0163>": 50421,
+  "<loc0164>": 50422,
+  "<loc0165>": 50423,
+  "<loc0166>": 50424,
+  "<loc0167>": 50425,
+  "<loc0168>": 50426,
+  "<loc0169>": 50427,
+  "<loc0170>": 50428,
+  "<loc0171>": 50429,
+  "<loc0172>": 50430,
+  "<loc0173>": 50431,
+  "<loc0174>": 50432,
+  "<loc0175>": 50433,
+  "<loc0176>": 50434,
+  "<loc0177>": 50435,
+  "<loc0178>": 50436,
+  "<loc0179>": 50437,
+  "<loc0180>": 50438,
+  "<loc0181>": 50439,
+  "<loc0182>": 50440,
+  "<loc0183>": 50441,
+  "<loc0184>": 50442,
+  "<loc0185>": 50443,
+  "<loc0186>": 50444,
+  "<loc0187>": 50445,
+  "<loc0188>": 50446,
+  "<loc0189>": 50447,
+  "<loc0190>": 50448,
+  "<loc0191>": 50449,
+  "<loc0192>": 50450,
+  "<loc0193>": 50451,
+  "<loc0194>": 50452,
+  "<loc0195>": 50453,
+  "<loc0196>": 50454,
+  "<loc0197>": 50455,
+  "<loc0198>": 50456,
+  "<loc0199>": 50457,
+  "<loc0200>": 50458,
+  "<loc0201>": 50459,
+  "<loc0202>": 50460,
+  "<loc0203>": 50461,
+  "<loc0204>": 50462,
+  "<loc0205>": 50463,
+  "<loc0206>": 50464,
+  "<loc0207>": 50465,
+  "<loc0208>": 50466,
+  "<loc0209>": 50467,
+  "<loc0210>": 50468,
+  "<loc0211>": 50469,
+  "<loc0212>": 50470,
+  "<loc0213>": 50471,
+  "<loc0214>": 50472,
+  "<loc0215>": 50473,
+  "<loc0216>": 50474,
+  "<loc0217>": 50475,
+  "<loc0218>": 50476,
+  "<loc0219>": 50477,
+  "<loc0220>": 50478,
+  "<loc0221>": 50479,
+  "<loc0222>": 50480,
+  "<loc0223>": 50481,
+  "<loc0224>": 50482,
+  "<loc0225>": 50483,
+  "<loc0226>": 50484,
+  "<loc0227>": 50485,
+  "<loc0228>": 50486,
+  "<loc0229>": 50487,
+  "<loc0230>": 50488,
+  "<loc0231>": 50489,
+  "<loc0232>": 50490,
+  "<loc0233>": 50491,
+  "<loc0234>": 50492,
+  "<loc0235>": 50493,
+  "<loc0236>": 50494,
+  "<loc0237>": 50495,
+  "<loc0238>": 50496,
+  "<loc0239>": 50497,
+  "<loc0240>": 50498,
+  "<loc0241>": 50499,
+  "<loc0242>": 50500,
+  "<loc0243>": 50501,
+  "<loc0244>": 50502,
+  "<loc0245>": 50503,
+  "<loc0246>": 50504,
+  "<loc0247>": 50505,
+  "<loc0248>": 50506,
+  "<loc0249>": 50507,
+  "<loc0250>": 50508,
+  "<loc0251>": 50509,
+  "<loc0252>": 50510,
+  "<loc0253>": 50511,
+  "<loc0254>": 50512,
+  "<loc0255>": 50513,
+  "<loc0256>": 50514,
+  "<loc0257>": 50515,
+  "<loc0258>": 50516,
+  "<loc0259>": 50517,
+  "<loc0260>": 50518,
+  "<loc0261>": 50519,
+  "<loc0262>": 50520,
+  "<loc0263>": 50521,
+  "<loc0264>": 50522,
+  "<loc0265>": 50523,
+  "<loc0266>": 50524,
+  "<loc0267>": 50525,
+  "<loc0268>": 50526,
+  "<loc0269>": 50527,
+  "<loc0270>": 50528,
+  "<loc0271>": 50529,
+  "<loc0272>": 50530,
+  "<loc0273>": 50531,
+  "<loc0274>": 50532,
+  "<loc0275>": 50533,
+  "<loc0276>": 50534,
+  "<loc0277>": 50535,
+  "<loc0278>": 50536,
+  "<loc0279>": 50537,
+  "<loc0280>": 50538,
+  "<loc0281>": 50539,
+  "<loc0282>": 50540,
+  "<loc0283>": 50541,
+  "<loc0284>": 50542,
+  "<loc0285>": 50543,
+  "<loc0286>": 50544,
+  "<loc0287>": 50545,
+  "<loc0288>": 50546,
+  "<loc0289>": 50547,
+  "<loc0290>": 50548,
+  "<loc0291>": 50549,
+  "<loc0292>": 50550,
+  "<loc0293>": 50551,
+  "<loc0294>": 50552,
+  "<loc0295>": 50553,
+  "<loc0296>": 50554,
+  "<loc0297>": 50555,
+  "<loc0298>": 50556,
+  "<loc0299>": 50557,
+  "<loc0300>": 50558,
+  "<loc0301>": 50559,
+  "<loc0302>": 50560,
+  "<loc0303>": 50561,
+  "<loc0304>": 50562,
+  "<loc0305>": 50563,
+  "<loc0306>": 50564,
+  "<loc0307>": 50565,
+  "<loc0308>": 50566,
+  "<loc0309>": 50567,
+  "<loc0310>": 50568,
+  "<loc0311>": 50569,
+  "<loc0312>": 50570,
+  "<loc0313>": 50571,
+  "<loc0314>": 50572,
+  "<loc0315>": 50573,
+  "<loc0316>": 50574,
+  "<loc0317>": 50575,
+  "<loc0318>": 50576,
+  "<loc0319>": 50577,
+  "<loc0320>": 50578,
+  "<loc0321>": 50579,
+  "<loc0322>": 50580,
+  "<loc0323>": 50581,
+  "<loc0324>": 50582,
+  "<loc0325>": 50583,
+  "<loc0326>": 50584,
+  "<loc0327>": 50585,
+  "<loc0328>": 50586,
+  "<loc0329>": 50587,
+  "<loc0330>": 50588,
+  "<loc0331>": 50589,
+  "<loc0332>": 50590,
+  "<loc0333>": 50591,
+  "<loc0334>": 50592,
+  "<loc0335>": 50593,
+  "<loc0336>": 50594,
+  "<loc0337>": 50595,
+  "<loc0338>": 50596,
+  "<loc0339>": 50597,
+  "<loc0340>": 50598,
+  "<loc0341>": 50599,
+  "<loc0342>": 50600,
+  "<loc0343>": 50601,
+  "<loc0344>": 50602,
+  "<loc0345>": 50603,
+  "<loc0346>": 50604,
+  "<loc0347>": 50605,
+  "<loc0348>": 50606,
+  "<loc0349>": 50607,
+  "<loc0350>": 50608,
+  "<loc0351>": 50609,
+  "<loc0352>": 50610,
+  "<loc0353>": 50611,
+  "<loc0354>": 50612,
+  "<loc0355>": 50613,
+  "<loc0356>": 50614,
+  "<loc0357>": 50615,
+  "<loc0358>": 50616,
+  "<loc0359>": 50617,
+  "<loc0360>": 50618,
+  "<loc0361>": 50619,
+  "<loc0362>": 50620,
+  "<loc0363>": 50621,
+  "<loc0364>": 50622,
+  "<loc0365>": 50623,
+  "<loc0366>": 50624,
+  "<loc0367>": 50625,
+  "<loc0368>": 50626,
+  "<loc0369>": 50627,
+  "<loc0370>": 50628,
+  "<loc0371>": 50629,
+  "<loc0372>": 50630,
+  "<loc0373>": 50631,
+  "<loc0374>": 50632,
+  "<loc0375>": 50633,
+  "<loc0376>": 50634,
+  "<loc0377>": 50635,
+  "<loc0378>": 50636,
+  "<loc0379>": 50637,
+  "<loc0380>": 50638,
+  "<loc0381>": 50639,
+  "<loc0382>": 50640,
+  "<loc0383>": 50641,
+  "<loc0384>": 50642,
+  "<loc0385>": 50643,
+  "<loc0386>": 50644,
+  "<loc0387>": 50645,
+  "<loc0388>": 50646,
+  "<loc0389>": 50647,
+  "<loc0390>": 50648,
+  "<loc0391>": 50649,
+  "<loc0392>": 50650,
+  "<loc0393>": 50651,
+  "<loc0394>": 50652,
+  "<loc0395>": 50653,
+  "<loc0396>": 50654,
+  "<loc0397>": 50655,
+  "<loc0398>": 50656,
+  "<loc0399>": 50657,
+  "<loc0400>": 50658,
+  "<loc0401>": 50659,
+  "<loc0402>": 50660,
+  "<loc0403>": 50661,
+  "<loc0404>": 50662,
+  "<loc0405>": 50663,
+  "<loc0406>": 50664,
+  "<loc0407>": 50665,
+  "<loc0408>": 50666,
+  "<loc0409>": 50667,
+  "<loc0410>": 50668,
+  "<loc0411>": 50669,
+  "<loc0412>": 50670,
+  "<loc0413>": 50671,
+  "<loc0414>": 50672,
+  "<loc0415>": 50673,
+  "<loc0416>": 50674,
+  "<loc0417>": 50675,
+  "<loc0418>": 50676,
+  "<loc0419>": 50677,
+  "<loc0420>": 50678,
+  "<loc0421>": 50679,
+  "<loc0422>": 50680,
+  "<loc0423>": 50681,
+  "<loc0424>": 50682,
+  "<loc0425>": 50683,
+  "<loc0426>": 50684,
+  "<loc0427>": 50685,
+  "<loc0428>": 50686,
+  "<loc0429>": 50687,
+  "<loc0430>": 50688,
+  "<loc0431>": 50689,
+  "<loc0432>": 50690,
+  "<loc0433>": 50691,
+  "<loc0434>": 50692,
+  "<loc0435>": 50693,
+  "<loc0436>": 50694,
+  "<loc0437>": 50695,
+  "<loc0438>": 50696,
+  "<loc0439>": 50697,
+  "<loc0440>": 50698,
+  "<loc0441>": 50699,
+  "<loc0442>": 50700,
+  "<loc0443>": 50701,
+  "<loc0444>": 50702,
+  "<loc0445>": 50703,
+  "<loc0446>": 50704,
+  "<loc0447>": 50705,
+  "<loc0448>": 50706,
+  "<loc0449>": 50707,
+  "<loc0450>": 50708,
+  "<loc0451>": 50709,
+  "<loc0452>": 50710,
+  "<loc0453>": 50711,
+  "<loc0454>": 50712,
+  "<loc0455>": 50713,
+  "<loc0456>": 50714,
+  "<loc0457>": 50715,
+  "<loc0458>": 50716,
+  "<loc0459>": 50717,
+  "<loc0460>": 50718,
+  "<loc0461>": 50719,
+  "<loc0462>": 50720,
+  "<loc0463>": 50721,
+  "<loc0464>": 50722,
+  "<loc0465>": 50723,
+  "<loc0466>": 50724,
+  "<loc0467>": 50725,
+  "<loc0468>": 50726,
+  "<loc0469>": 50727,
+  "<loc0470>": 50728,
+  "<loc0471>": 50729,
+  "<loc0472>": 50730,
+  "<loc0473>": 50731,
+  "<loc0474>": 50732,
+  "<loc0475>": 50733,
+  "<loc0476>": 50734,
+  "<loc0477>": 50735,
+  "<loc0478>": 50736,
+  "<loc0479>": 50737,
+  "<loc0480>": 50738,
+  "<loc0481>": 50739,
+  "<loc0482>": 50740,
+  "<loc0483>": 50741,
+  "<loc0484>": 50742,
+  "<loc0485>": 50743,
+  "<loc0486>": 50744,
+  "<loc0487>": 50745,
+  "<loc0488>": 50746,
+  "<loc0489>": 50747,
+  "<loc0490>": 50748,
+  "<loc0491>": 50749,
+  "<loc0492>": 50750,
+  "<loc0493>": 50751,
+  "<loc0494>": 50752,
+  "<loc0495>": 50753,
+  "<loc0496>": 50754,
+  "<loc0497>": 50755,
+  "<loc0498>": 50756,
+  "<loc0499>": 50757,
+  "<loc0500>": 50758,
+  "<loc0501>": 50759,
+  "<loc0502>": 50760,
+  "<loc0503>": 50761,
+  "<loc0504>": 50762,
+  "<loc0505>": 50763,
+  "<loc0506>": 50764,
+  "<loc0507>": 50765,
+  "<loc0508>": 50766,
+  "<loc0509>": 50767,
+  "<loc0510>": 50768,
+  "<loc0511>": 50769,
+  "<loc0512>": 50770,
+  "<loc0513>": 50771,
+  "<loc0514>": 50772,
+  "<loc0515>": 50773,
+  "<loc0516>": 50774,
+  "<loc0517>": 50775,
+  "<loc0518>": 50776,
+  "<loc0519>": 50777,
+  "<loc0520>": 50778,
+  "<loc0521>": 50779,
+  "<loc0522>": 50780,
+  "<loc0523>": 50781,
+  "<loc0524>": 50782,
+  "<loc0525>": 50783,
+  "<loc0526>": 50784,
+  "<loc0527>": 50785,
+  "<loc0528>": 50786,
+  "<loc0529>": 50787,
+  "<loc0530>": 50788,
+  "<loc0531>": 50789,
+  "<loc0532>": 50790,
+  "<loc0533>": 50791,
+  "<loc0534>": 50792,
+  "<loc0535>": 50793,
+  "<loc0536>": 50794,
+  "<loc0537>": 50795,
+  "<loc0538>": 50796,
+  "<loc0539>": 50797,
+  "<loc0540>": 50798,
+  "<loc0541>": 50799,
+  "<loc0542>": 50800,
+  "<loc0543>": 50801,
+  "<loc0544>": 50802,
+  "<loc0545>": 50803,
+  "<loc0546>": 50804,
+  "<loc0547>": 50805,
+  "<loc0548>": 50806,
+  "<loc0549>": 50807,
+  "<loc0550>": 50808,
+  "<loc0551>": 50809,
+  "<loc0552>": 50810,
+  "<loc0553>": 50811,
+  "<loc0554>": 50812,
+  "<loc0555>": 50813,
+  "<loc0556>": 50814,
+  "<loc0557>": 50815,
+  "<loc0558>": 50816,
+  "<loc0559>": 50817,
+  "<loc0560>": 50818,
+  "<loc0561>": 50819,
+  "<loc0562>": 50820,
+  "<loc0563>": 50821,
+  "<loc0564>": 50822,
+  "<loc0565>": 50823,
+  "<loc0566>": 50824,
+  "<loc0567>": 50825,
+  "<loc0568>": 50826,
+  "<loc0569>": 50827,
+  "<loc0570>": 50828,
+  "<loc0571>": 50829,
+  "<loc0572>": 50830,
+  "<loc0573>": 50831,
+  "<loc0574>": 50832,
+  "<loc0575>": 50833,
+  "<loc0576>": 50834,
+  "<loc0577>": 50835,
+  "<loc0578>": 50836,
+  "<loc0579>": 50837,
+  "<loc0580>": 50838,
+  "<loc0581>": 50839,
+  "<loc0582>": 50840,
+  "<loc0583>": 50841,
+  "<loc0584>": 50842,
+  "<loc0585>": 50843,
+  "<loc0586>": 50844,
+  "<loc0587>": 50845,
+  "<loc0588>": 50846,
+  "<loc0589>": 50847,
+  "<loc0590>": 50848,
+  "<loc0591>": 50849,
+  "<loc0592>": 50850,
+  "<loc0593>": 50851,
+  "<loc0594>": 50852,
+  "<loc0595>": 50853,
+  "<loc0596>": 50854,
+  "<loc0597>": 50855,
+  "<loc0598>": 50856,
+  "<loc0599>": 50857,
+  "<loc0600>": 50858,
+  "<loc0601>": 50859,
+  "<loc0602>": 50860,
+  "<loc0603>": 50861,
+  "<loc0604>": 50862,
+  "<loc0605>": 50863,
+  "<loc0606>": 50864,
+  "<loc0607>": 50865,
+  "<loc0608>": 50866,
+  "<loc0609>": 50867,
+  "<loc0610>": 50868,
+  "<loc0611>": 50869,
+  "<loc0612>": 50870,
+  "<loc0613>": 50871,
+  "<loc0614>": 50872,
+  "<loc0615>": 50873,
+  "<loc0616>": 50874,
+  "<loc0617>": 50875,
+  "<loc0618>": 50876,
+  "<loc0619>": 50877,
+  "<loc0620>": 50878,
+  "<loc0621>": 50879,
+  "<loc0622>": 50880,
+  "<loc0623>": 50881,
+  "<loc0624>": 50882,
+  "<loc0625>": 50883,
+  "<loc0626>": 50884,
+  "<loc0627>": 50885,
+  "<loc0628>": 50886,
+  "<loc0629>": 50887,
+  "<loc0630>": 50888,
+  "<loc0631>": 50889,
+  "<loc0632>": 50890,
+  "<loc0633>": 50891,
+  "<loc0634>": 50892,
+  "<loc0635>": 50893,
+  "<loc0636>": 50894,
+  "<loc0637>": 50895,
+  "<loc0638>": 50896,
+  "<loc0639>": 50897,
+  "<loc0640>": 50898,
+  "<loc0641>": 50899,
+  "<loc0642>": 50900,
+  "<loc0643>": 50901,
+  "<loc0644>": 50902,
+  "<loc0645>": 50903,
+  "<loc0646>": 50904,
+  "<loc0647>": 50905,
+  "<loc0648>": 50906,
+  "<loc0649>": 50907,
+  "<loc0650>": 50908,
+  "<loc0651>": 50909,
+  "<loc0652>": 50910,
+  "<loc0653>": 50911,
+  "<loc0654>": 50912,
+  "<loc0655>": 50913,
+  "<loc0656>": 50914,
+  "<loc0657>": 50915,
+  "<loc0658>": 50916,
+  "<loc0659>": 50917,
+  "<loc0660>": 50918,
+  "<loc0661>": 50919,
+  "<loc0662>": 50920,
+  "<loc0663>": 50921,
+  "<loc0664>": 50922,
+  "<loc0665>": 50923,
+  "<loc0666>": 50924,
+  "<loc0667>": 50925,
+  "<loc0668>": 50926,
+  "<loc0669>": 50927,
+  "<loc0670>": 50928,
+  "<loc0671>": 50929,
+  "<loc0672>": 50930,
+  "<loc0673>": 50931,
+  "<loc0674>": 50932,
+  "<loc0675>": 50933,
+  "<loc0676>": 50934,
+  "<loc0677>": 50935,
+  "<loc0678>": 50936,
+  "<loc0679>": 50937,
+  "<loc0680>": 50938,
+  "<loc0681>": 50939,
+  "<loc0682>": 50940,
+  "<loc0683>": 50941,
+  "<loc0684>": 50942,
+  "<loc0685>": 50943,
+  "<loc0686>": 50944,
+  "<loc0687>": 50945,
+  "<loc0688>": 50946,
+  "<loc0689>": 50947,
+  "<loc0690>": 50948,
+  "<loc0691>": 50949,
+  "<loc0692>": 50950,
+  "<loc0693>": 50951,
+  "<loc0694>": 50952,
+  "<loc0695>": 50953,
+  "<loc0696>": 50954,
+  "<loc0697>": 50955,
+  "<loc0698>": 50956,
+  "<loc0699>": 50957,
+  "<loc0700>": 50958,
+  "<loc0701>": 50959,
+  "<loc0702>": 50960,
+  "<loc0703>": 50961,
+  "<loc0704>": 50962,
+  "<loc0705>": 50963,
+  "<loc0706>": 50964,
+  "<loc0707>": 50965,
+  "<loc0708>": 50966,
+  "<loc0709>": 50967,
+  "<loc0710>": 50968,
+  "<loc0711>": 50969,
+  "<loc0712>": 50970,
+  "<loc0713>": 50971,
+  "<loc0714>": 50972,
+  "<loc0715>": 50973,
+  "<loc0716>": 50974,
+  "<loc0717>": 50975,
+  "<loc0718>": 50976,
+  "<loc0719>": 50977,
+  "<loc0720>": 50978,
+  "<loc0721>": 50979,
+  "<loc0722>": 50980,
+  "<loc0723>": 50981,
+  "<loc0724>": 50982,
+  "<loc0725>": 50983,
+  "<loc0726>": 50984,
+  "<loc0727>": 50985,
+  "<loc0728>": 50986,
+  "<loc0729>": 50987,
+  "<loc0730>": 50988,
+  "<loc0731>": 50989,
+  "<loc0732>": 50990,
+  "<loc0733>": 50991,
+  "<loc0734>": 50992,
+  "<loc0735>": 50993,
+  "<loc0736>": 50994,
+  "<loc0737>": 50995,
+  "<loc0738>": 50996,
+  "<loc0739>": 50997,
+  "<loc0740>": 50998,
+  "<loc0741>": 50999,
+  "<loc0742>": 51000,
+  "<loc0743>": 51001,
+  "<loc0744>": 51002,
+  "<loc0745>": 51003,
+  "<loc0746>": 51004,
+  "<loc0747>": 51005,
+  "<loc0748>": 51006,
+  "<loc0749>": 51007,
+  "<loc0750>": 51008,
+  "<loc0751>": 51009,
+  "<loc0752>": 51010,
+  "<loc0753>": 51011,
+  "<loc0754>": 51012,
+  "<loc0755>": 51013,
+  "<loc0756>": 51014,
+  "<loc0757>": 51015,
+  "<loc0758>": 51016,
+  "<loc0759>": 51017,
+  "<loc0760>": 51018,
+  "<loc0761>": 51019,
+  "<loc0762>": 51020,
+  "<loc0763>": 51021,
+  "<loc0764>": 51022,
+  "<loc0765>": 51023,
+  "<loc0766>": 51024,
+  "<loc0767>": 51025,
+  "<loc0768>": 51026,
+  "<loc0769>": 51027,
+  "<loc0770>": 51028,
+  "<loc0771>": 51029,
+  "<loc0772>": 51030,
+  "<loc0773>": 51031,
+  "<loc0774>": 51032,
+  "<loc0775>": 51033,
+  "<loc0776>": 51034,
+  "<loc0777>": 51035,
+  "<loc0778>": 51036,
+  "<loc0779>": 51037,
+  "<loc0780>": 51038,
+  "<loc0781>": 51039,
+  "<loc0782>": 51040,
+  "<loc0783>": 51041,
+  "<loc0784>": 51042,
+  "<loc0785>": 51043,
+  "<loc0786>": 51044,
+  "<loc0787>": 51045,
+  "<loc0788>": 51046,
+  "<loc0789>": 51047,
+  "<loc0790>": 51048,
+  "<loc0791>": 51049,
+  "<loc0792>": 51050,
+  "<loc0793>": 51051,
+  "<loc0794>": 51052,
+  "<loc0795>": 51053,
+  "<loc0796>": 51054,
+  "<loc0797>": 51055,
+  "<loc0798>": 51056,
+  "<loc0799>": 51057,
+  "<loc0800>": 51058,
+  "<loc0801>": 51059,
+  "<loc0802>": 51060,
+  "<loc0803>": 51061,
+  "<loc0804>": 51062,
+  "<loc0805>": 51063,
+  "<loc0806>": 51064,
+  "<loc0807>": 51065,
+  "<loc0808>": 51066,
+  "<loc0809>": 51067,
+  "<loc0810>": 51068,
+  "<loc0811>": 51069,
+  "<loc0812>": 51070,
+  "<loc0813>": 51071,
+  "<loc0814>": 51072,
+  "<loc0815>": 51073,
+  "<loc0816>": 51074,
+  "<loc0817>": 51075,
+  "<loc0818>": 51076,
+  "<loc0819>": 51077,
+  "<loc0820>": 51078,
+  "<loc0821>": 51079,
+  "<loc0822>": 51080,
+  "<loc0823>": 51081,
+  "<loc0824>": 51082,
+  "<loc0825>": 51083,
+  "<loc0826>": 51084,
+  "<loc0827>": 51085,
+  "<loc0828>": 51086,
+  "<loc0829>": 51087,
+  "<loc0830>": 51088,
+  "<loc0831>": 51089,
+  "<loc0832>": 51090,
+  "<loc0833>": 51091,
+  "<loc0834>": 51092,
+  "<loc0835>": 51093,
+  "<loc0836>": 51094,
+  "<loc0837>": 51095,
+  "<loc0838>": 51096,
+  "<loc0839>": 51097,
+  "<loc0840>": 51098,
+  "<loc0841>": 51099,
+  "<loc0842>": 51100,
+  "<loc0843>": 51101,
+  "<loc0844>": 51102,
+  "<loc0845>": 51103,
+  "<loc0846>": 51104,
+  "<loc0847>": 51105,
+  "<loc0848>": 51106,
+  "<loc0849>": 51107,
+  "<loc0850>": 51108,
+  "<loc0851>": 51109,
+  "<loc0852>": 51110,
+  "<loc0853>": 51111,
+  "<loc0854>": 51112,
+  "<loc0855>": 51113,
+  "<loc0856>": 51114,
+  "<loc0857>": 51115,
+  "<loc0858>": 51116,
+  "<loc0859>": 51117,
+  "<loc0860>": 51118,
+  "<loc0861>": 51119,
+  "<loc0862>": 51120,
+  "<loc0863>": 51121,
+  "<loc0864>": 51122,
+  "<loc0865>": 51123,
+  "<loc0866>": 51124,
+  "<loc0867>": 51125,
+  "<loc0868>": 51126,
+  "<loc0869>": 51127,
+  "<loc0870>": 51128,
+  "<loc0871>": 51129,
+  "<loc0872>": 51130,
+  "<loc0873>": 51131,
+  "<loc0874>": 51132,
+  "<loc0875>": 51133,
+  "<loc0876>": 51134,
+  "<loc0877>": 51135,
+  "<loc0878>": 51136,
+  "<loc0879>": 51137,
+  "<loc0880>": 51138,
+  "<loc0881>": 51139,
+  "<loc0882>": 51140,
+  "<loc0883>": 51141,
+  "<loc0884>": 51142,
+  "<loc0885>": 51143,
+  "<loc0886>": 51144,
+  "<loc0887>": 51145,
+  "<loc0888>": 51146,
+  "<loc0889>": 51147,
+  "<loc0890>": 51148,
+  "<loc0891>": 51149,
+  "<loc0892>": 51150,
+  "<loc0893>": 51151,
+  "<loc0894>": 51152,
+  "<loc0895>": 51153,
+  "<loc0896>": 51154,
+  "<loc0897>": 51155,
+  "<loc0898>": 51156,
+  "<loc0899>": 51157,
+  "<loc0900>": 51158,
+  "<loc0901>": 51159,
+  "<loc0902>": 51160,
+  "<loc0903>": 51161,
+  "<loc0904>": 51162,
+  "<loc0905>": 51163,
+  "<loc0906>": 51164,
+  "<loc0907>": 51165,
+  "<loc0908>": 51166,
+  "<loc0909>": 51167,
+  "<loc0910>": 51168,
+  "<loc0911>": 51169,
+  "<loc0912>": 51170,
+  "<loc0913>": 51171,
+  "<loc0914>": 51172,
+  "<loc0915>": 51173,
+  "<loc0916>": 51174,
+  "<loc0917>": 51175,
+  "<loc0918>": 51176,
+  "<loc0919>": 51177,
+  "<loc0920>": 51178,
+  "<loc0921>": 51179,
+  "<loc0922>": 51180,
+  "<loc0923>": 51181,
+  "<loc0924>": 51182,
+  "<loc0925>": 51183,
+  "<loc0926>": 51184,
+  "<loc0927>": 51185,
+  "<loc0928>": 51186,
+  "<loc0929>": 51187,
+  "<loc0930>": 51188,
+  "<loc0931>": 51189,
+  "<loc0932>": 51190,
+  "<loc0933>": 51191,
+  "<loc0934>": 51192,
+  "<loc0935>": 51193,
+  "<loc0936>": 51194,
+  "<loc0937>": 51195,
+  "<loc0938>": 51196,
+  "<loc0939>": 51197,
+  "<loc0940>": 51198,
+  "<loc0941>": 51199,
+  "<loc0942>": 51200,
+  "<loc0943>": 51201,
+  "<loc0944>": 51202,
+  "<loc0945>": 51203,
+  "<loc0946>": 51204,
+  "<loc0947>": 51205,
+  "<loc0948>": 51206,
+  "<loc0949>": 51207,
+  "<loc0950>": 51208,
+  "<loc0951>": 51209,
+  "<loc0952>": 51210,
+  "<loc0953>": 51211,
+  "<loc0954>": 51212,
+  "<loc0955>": 51213,
+  "<loc0956>": 51214,
+  "<loc0957>": 51215,
+  "<loc0958>": 51216,
+  "<loc0959>": 51217,
+  "<loc0960>": 51218,
+  "<loc0961>": 51219,
+  "<loc0962>": 51220,
+  "<loc0963>": 51221,
+  "<loc0964>": 51222,
+  "<loc0965>": 51223,
+  "<loc0966>": 51224,
+  "<loc0967>": 51225,
+  "<loc0968>": 51226,
+  "<loc0969>": 51227,
+  "<loc0970>": 51228,
+  "<loc0971>": 51229,
+  "<loc0972>": 51230,
+  "<loc0973>": 51231,
+  "<loc0974>": 51232,
+  "<loc0975>": 51233,
+  "<loc0976>": 51234,
+  "<loc0977>": 51235,
+  "<loc0978>": 51236,
+  "<loc0979>": 51237,
+  "<loc0980>": 51238,
+  "<loc0981>": 51239,
+  "<loc0982>": 51240,
+  "<loc0983>": 51241,
+  "<loc0984>": 51242,
+  "<loc0985>": 51243,
+  "<loc0986>": 51244,
+  "<loc0987>": 51245,
+  "<loc0988>": 51246,
+  "<loc0989>": 51247,
+  "<loc0990>": 51248,
+  "<loc0991>": 51249,
+  "<loc0992>": 51250,
+  "<loc0993>": 51251,
+  "<loc0994>": 51252,
+  "<loc0995>": 51253,
+  "<loc0996>": 51254,
+  "<loc0997>": 51255,
+  "<loc0998>": 51256,
+  "<loc0999>": 51257,
+  "<loc1000>": 51258,
+  "<loc1001>": 51259,
+  "<loc1002>": 51260,
+  "<loc1003>": 51261,
+  "<loc1004>": 51262,
+  "<loc1005>": 51263,
+  "<loc1006>": 51264,
+  "<loc1007>": 51265,
+  "<loc1008>": 51266,
+  "<loc1009>": 51267,
+  "<loc1010>": 51268,
+  "<loc1011>": 51269,
+  "<loc1012>": 51270,
+  "<loc1013>": 51271,
+  "<loc1014>": 51272,
+  "<loc1015>": 51273,
+  "<loc1016>": 51274,
+  "<loc1017>": 51275,
+  "<loc1018>": 51276,
+  "<loc1019>": 51277,
+  "<loc1020>": 51278,
+  "<loc1021>": 51279,
+  "<loc1022>": 51280,
+  "<loc1023>": 51281
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "auto_map": {
+    "AutoProcessor": "processing_travisionlm.TraVisionProcessor"
+  },
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "TraVisionProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

processing_travisionlm.py ADDED Viewed

	@@ -0,0 +1,276 @@

+"""
+Processor class for TraVisionLM.
+"""
+import logging
+from typing import List, Optional, Union
+from transformers.feature_extraction_utils import BatchFeature
+from transformers.image_utils import ImageInput, is_valid_image
+from transformers.processing_utils import ProcessorMixin
+from transformers.tokenization_utils import (
+    AddedToken,
+    PaddingStrategy,
+    PreTokenizedInput,
+    TextInput,
+    TruncationStrategy,
+)
+from transformers.utils import TensorType
+logger = logging.getLogger(__name__)
+IMAGE_TOKEN = "<image>"
+EXTRA_TOKENS = [f"<loc{i:0>4}>" for i in range(1024)] # for object detection task
+# Copied from transformers.models.idefics2.processing_idefics2.is_url
+def is_url(val) -> bool:
+    return isinstance(val, str) and val.startswith("http")
+# Copied from transformers.models.idefics2.processing_idefics2.is_image_or_image_url
+def is_image_or_image_url(elem):
+    return is_url(elem) or is_valid_image(elem)
+# Copied from transformers.models.paligemma.processing_paligemma._is_str_or_image
+def _is_str_or_image(elem):
+    return isinstance(elem, (str)) or is_image_or_image_url(elem)
+def build_string_from_input(image_seq_len, image_token):
+    """
+    Builds a string from the input prompt and image tokens.
+    For example, for the call:
+    build_string_from_input(
+        image_seq_len=3,
+        image_token="<im>",
+    )
+    The output will be:
+    "<im><im><im>"
+    Args:
+        image_seq_len (`int`): The length of the image sequence.
+        image_token (`str`): The image token.
+    """
+    return f"{image_token * image_seq_len}"
+class TraVisionProcessor(ProcessorMixin):
+    r"""
+    Constructs a TraVision processor which wraps a SigLIP image processor and a GPT2 tokenizer into a single processor.
+    [`TraVisionProcessor`] offers all the functionalities of [`SiglipImageProcessor`] and [`GPT2TokenizerFast`]. See the
+    [`~TraVisionProcessor.__call__`] and [`~TraVisionProcessor.decode`] for more information.
+    Args:
+        image_processor ([`SiglipImageProcessor`], *optional*):
+            The image processor is a required input.
+        tokenizer ([`GPT2TokenizerFast`], *optional*):
+            The tokenizer is a required input.
+        chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages
+            in a chat into a tokenizable string.
+    """
+    attributes = ["image_processor", "tokenizer"]
+    valid_kwargs = ["chat_template"]
+    image_processor_class = "SiglipImageProcessor"
+    tokenizer_class = ("GPT2Tokenizer", "GPT2TokenizerFast")
+    def __init__(
+        self,
+        image_processor=None,
+        tokenizer=None,
+        chat_template=None,
+        **kwargs,
+    ):
+        if image_processor is None:
+            raise ValueError("You need to specify an `image_processor`.")
+        if tokenizer is None:
+            raise ValueError("You need to specify a `tokenizer`.")
+        if not hasattr(image_processor, "image_seq_length"):
+            raise ValueError("Image processor is missing an `image_seq_length` attribute.")
+        self.image_seq_length = image_processor.image_seq_length
+        image_token = AddedToken(IMAGE_TOKEN, normalized=False, special=True)
+        tokens_to_add = {"additional_special_tokens": [image_token]}
+        tokenizer.add_special_tokens(tokens_to_add)
+        tokenizer.add_tokens(EXTRA_TOKENS)
+        self.image_token_id = tokenizer.convert_tokens_to_ids(IMAGE_TOKEN)
+        tokenizer.add_bos_token = False
+        tokenizer.add_eos_token = False
+        super().__init__(image_processor, tokenizer, chat_template=chat_template)
+    def __call__(
+        self,
+        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
+        images: ImageInput = None,
+        tokenize_newline_separately: bool = True,
+        padding: Union[bool, str, PaddingStrategy] = False,
+        truncation: Union[bool, str, TruncationStrategy] = None,
+        max_length=None,
+        return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
+        do_resize: bool = None,
+        do_normalize: bool = None,
+        image_mean: Optional[Union[float, List[float]]] = None,
+        image_std: Optional[Union[float, List[float]]] = None,
+        data_format: Optional["ChannelDimension"] = "channels_first",  # noqa: F821
+        input_data_format: Optional[
+            Union[str, "ChannelDimension"]  # noqa: F821
+        ] = None,
+        resample: "PILImageResampling" = None,  # noqa: F821
+        do_convert_rgb: bool = None,
+        do_thumbnail: bool = None,
+        do_align_long_axis: bool = None,
+        do_rescale: bool = None,
+        labels: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
+    ) -> BatchFeature:
+        """
+        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
+        and `kwargs` arguments to GPT2TokenizerFast's [`~GPT2TokenizerFast.__call__`] if `text` is not `None` to encode
+        the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
+        SiglipImageProcessor's [`~SiglipImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
+        of the above two methods for more information.
+        The usage for TraVisionLM fine-tuning preparation follows a standard 4D causal mask where only the prompt and label tokens
+        are attended in an auto-regressive manner. The label in `text` are to be passed separately to the __call__ function and
+        will be placed after the prompt, which is the instruction to steer the model generation.
+        Args:
+            text (`str`, `List[str]`, `List[List[str]]`):
+                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
+                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
+                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
+            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
+                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
+                tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
+                number of channels, H and W are image height and width.
+            tokenize_newline_separately (`bool`, defaults to `True`):
+                Adds a separately tokenized '\n' at the end of the prompt.
+            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
+                Select a strategy to pad the returned sequences (according to the model's padding side and padding
+                index) among:
+                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
+                  sequence if provided).
+                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
+                  acceptable input length for the model if that argument is not provided.
+                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
+                  lengths).
+            max_length (`int`, *optional*):
+                Maximum length of the returned list and optionally padding length (see above).
+            truncation (`bool`, *optional*):
+                Activates truncation to cut input sequences longer than `max_length` to `max_length`.
+            return_tensors (`str` or [`~utils.TensorType`], *optional*):
+                If set, will return tensors of a particular framework. Acceptable values are:
+                - `'tf'`: Return TensorFlow `tf.constant` objects.
+                - `'pt'`: Return PyTorch `torch.Tensor` objects.
+                - `'np'`: Return NumPy `np.ndarray` objects.
+                - `'jax'`: Return JAX `jnp.ndarray` objects.
+            label (`str`, `List[str]`, `List[List[str]]`):
+                The label or batch of labels to be encoded. Only necessary for training.
+                for more information. If your prompt is "<image> Resimde ne var", the label corresponds to the expected prediction "çimlerde uzanan bir köpek".
+        Returns:
+            [`BatchFeature`]: A [`BatchFeature`] with the following fields:
+            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. If `label`
+              is provided, the `input_ids` will also contain the label input ids.
+            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
+              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
+              `None`).
+            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
+            - **labels** -- Labels compatible with training if `label` is not None
+        """
+        # return_token_type_ids = True if labels is not None else False
+        return_token_type_ids = True
+        if images is None:
+            raise ValueError("`images` are expected as arguments to a `TraVisionProcessor` instance.")
+        if text is None:
+            logger.warning_once(
+                "You are using TraVisionLM without a text prefix. It will perform as a picture-captioning model."
+            )
+            text = "Açıkla"  # default prompt if it is not provided as an argument
+        if isinstance(text, List) and isinstance(images, List):
+            if len(images) < len(text):
+                raise ValueError(
+                    f"Received {len(images)} images for {len(text)} prompts. Each prompt should be associated with an image."
+                )
+        if _is_str_or_image(text):
+            text = [text]
+        elif isinstance(text, list) and _is_str_or_image(text[0]):
+            pass
+        text = [f"{prompt}\n" for prompt in text]
+        if labels is not None and _is_str_or_image(labels):
+            labels = [labels]
+        if labels is not None:
+            labels = [label + self.tokenizer.eos_token for label in labels]
+            text = [f"{prompt}{label}" for prompt, label in zip(text, labels)]
+        input_strings = [
+            build_string_from_input(
+                image_seq_len=self.image_seq_length,
+                image_token=IMAGE_TOKEN,
+            )
+            for _ in text
+        ]
+        pixel_values = self.image_processor(
+            images,
+            do_resize=do_resize,
+            do_normalize=do_normalize,
+            return_tensors=return_tensors,
+            image_mean=image_mean,
+            image_std=image_std,
+            input_data_format=input_data_format,
+            data_format=data_format,
+            resample=resample,
+            do_convert_rgb=do_convert_rgb,
+        )["pixel_values"]
+        if max_length is not None:
+            max_length += self.image_seq_length  # max_length has to account for the image tokens
+        inputs = self.tokenizer(
+            input_strings,
+            text_pair=text,
+            return_tensors=return_tensors,
+            padding=padding,
+            max_length=max_length,
+            truncation=truncation,
+            return_token_type_ids=return_token_type_ids,
+        )
+        return_data = {**inputs, "pixel_values": pixel_values}
+        if labels is not None:
+            labels = inputs["input_ids"].masked_fill(inputs["token_type_ids"] == 0, -100)
+            return_data.update({"labels": labels})
+        return BatchFeature(data=return_data)
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->GPT2
+    def batch_decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to GPT2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
+        refer to the docstring of this method for more information.
+        """
+        return self.tokenizer.batch_decode(*args, **kwargs)
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.decode with CLIP->GPT2
+    def decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to GPT2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
+        the docstring of this method for more information.
+        """
+        return self.tokenizer.decode(*args, **kwargs)
+    @property
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names with CLIP->TraVision
+    def model_input_names(self):
+        tokenizer_input_names = self.tokenizer.model_input_names
+        image_processor_input_names = self.image_processor.model_input_names
+        return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))

processor_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "auto_map": {
+    "AutoProcessor": "processing_travisionlm.TraVisionProcessor"
+  },
+  "processor_class": "TraVisionProcessor"
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

The diff for this file is too large to render. See raw diff

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff