goldfish-models commited on
Commit
771e7e3
1 Parent(s): 64a84e7

Upload zsm_latn_5mb tokenizer.

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[XXXXX334]": 48311, "[XXXXX350]": 48327, "[XXXXX821]": 48798, "[XXXXX290]": 48267, "[XXXXX322]": 48299, "[MASK]": 47976, "[XXXXX1098]": 49075, "[XXXXX320]": 48297, "[XXXXX633]": 48610, "[XXXXX561]": 48538, "[XXXXX226]": 48203, "[XXXXX1063]": 49040, "[XXXXX9]": 47986, "[XXXXX1075]": 49052, "[XXXXX242]": 48219, "[XXXXX1066]": 49043, "[XXXXX720]": 48697, "[XXXXX899]": 48876, "[XXXXX385]": 48362, "[XXXXX375]": 48352, "[XXXXX672]": 48649, "[XXXXX663]": 48640, "[XXXXX965]": 48942, "[XXXXX757]": 48734, "[XXXXX566]": 48543, "[XXXXX446]": 48423, "[XXXXX124]": 48101, "[XXXXX697]": 48674, "[XXXXX1100]": 49077, "[XXXXX460]": 48437, "[XXXXX958]": 48935, "[XXXXX891]": 48868, "[XXXXX256]": 48233, "[XXXXX564]": 48541, "[XXXXX489]": 48466, "[XXXXX746]": 48723, "[XXXXX239]": 48216, "[XXXXX70]": 48047, "[XXXXX366]": 48343, "[XXXXX61]": 48038, "[XXXXX306]": 48283, "[XXXXX880]": 48857, "[XXXXX275]": 48252, "[XXXXX596]": 48573, "[XXXXX380]": 48357, "[XXXXX519]": 48496, "[XXXXX671]": 48648, "[XXXXX691]": 48668, "[XXXXX1143]": 49120, "[XXXXX540]": 48517, "[XXXXX621]": 48598, "[XXXXX928]": 48905, "[XXXXX943]": 48920, "[XXXXX135]": 48112, "[XXXXX437]": 48414, "[XXXXX167]": 48144, "[XXXXX1073]": 49050, "[XXXXX449]": 48426, "[SEP]": 47974, "[XXXXX186]": 48163, "[XXXXX456]": 48433, "[XXXXX1172]": 49149, "[XXXXX1037]": 49014, "[XXXXX774]": 48751, "[XXXXX559]": 48536, "[XXXXX673]": 48650, "[XXXXX418]": 48395, "[XXXXX94]": 48071, "[XXXXX408]": 48385, "[XXXXX698]": 48675, "[XXXXX485]": 48462, "[XXXXX863]": 48840, "[XXXXX404]": 48381, "[XXXXX728]": 48705, "[XXXXX802]": 48779, "[XXXXX785]": 48762, "[XXXXX575]": 48552, "[XXXXX541]": 48518, "[XXXXX992]": 48969, "[XXXXX117]": 48094, "[XXXXX181]": 48158, "[XXXXX22]": 47999, "[XXXXX228]": 48205, "[XXXXX431]": 48408, "[XXXXX616]": 48593, "[XXXXX397]": 48374, "[XXXXX853]": 48830, "[XXXXX325]": 48302, "[XXXXX1061]": 49038, "[XXXXX71]": 48048, "[XXXXX801]": 48778, "[XXXXX391]": 48368, "[XXXXX141]": 48118, "[XXXXX1123]": 49100, "[XXXXX352]": 48329, "[XXXXX689]": 48666, "[XXXXX54]": 48031, "[XXXXX423]": 48400, "[XXXXX611]": 48588, "[XXXXX1064]": 49041, "[XXXXX1167]": 49144, "[XXXXX196]": 48173, "[XXXXX195]": 48172, "[XXXXX879]": 48856, "[XXXXX602]": 48579, "[XXXXX1085]": 49062, "[XXXXX562]": 48539, "[XXXXX772]": 48749, "[XXXXX110]": 48087, "[XXXXX670]": 48647, "[XXXXX665]": 48642, "[XXXXX896]": 48873, "[XXXXX26]": 48003, "[XXXXX563]": 48540, "[XXXXX51]": 48028, "[XXXXX136]": 48113, "[XXXXX190]": 48167, "[XXXXX244]": 48221, "[XXXXX834]": 48811, "[XXXXX147]": 48124, "[XXXXX580]": 48557, "[XXXXX986]": 48963, "[XXXXX199]": 48176, "[XXXXX130]": 48107, "[XXXXX825]": 48802, "[XXXXX703]": 48680, "[XXXXX870]": 48847, "[XXXXX975]": 48952, "[XXXXX13]": 47990, "[XXXXX550]": 48527, "[XXXXX542]": 48519, "[XXXXX529]": 48506, "[XXXXX1054]": 49031, "[XXXXX1118]": 49095, "[XXXXX146]": 48123, "[XXXXX678]": 48655, "[XXXXX1144]": 49121, "[XXXXX486]": 48463, "[XXXXX1116]": 49093, "[XXXXX635]": 48612, "[XXXXX451]": 48428, "[XXXXX775]": 48752, "[XXXXX448]": 48425, "[XXXXX959]": 48936, "[XXXXX716]": 48693, "[XXXXX554]": 48531, "[XXXXX356]": 48333, "[XXXXX165]": 48142, "[XXXXX67]": 48044, "[XXXXX120]": 48097, "[XXXXX784]": 48761, "[XXXXX625]": 48602, "[XXXXX493]": 48470, "[XXXXX33]": 48010, "[XXXXX41]": 48018, "[XXXXX401]": 48378, "[XXXXX1065]": 49042, "[XXXXX403]": 48380, "[XXXXX795]": 48772, "[XXXXX968]": 48945, "[XXXXX732]": 48709, "[XXXXX594]": 48571, "[XXXXX359]": 48336, "[XXXXX419]": 48396, "[XXXXX804]": 48781, "[XXXXX618]": 48595, "[XXXXX950]": 48927, "[XXXXX763]": 48740, "[XXXXX683]": 48660, "[XXXXX417]": 48394, "[XXXXX927]": 48904, "[XXXXX1151]": 49128, "[XXXXX609]": 48586, "[XXXXX613]": 48590, "[XXXXX781]": 48758, "[XXXXX792]": 48769, "[XXXXX606]": 48583, "[XXXXX733]": 48710, "[XXXXX406]": 48383, "[XXXXX384]": 48361, "[XXXXX535]": 48512, "[XXXXX224]": 48201, "[XXXXX23]": 48000, "[XXXXX892]": 48869, "[XXXXX1039]": 49016, "[XXXXX636]": 48613, "[XXXXX607]": 48584, "[XXXXX450]": 48427, "[XXXXX132]": 48109, "[XXXXX232]": 48209, "[XXXXX5]": 47982, "[XXXXX477]": 48454, "[XXXXX445]": 48422, "[XXXXX452]": 48429, "[XXXXX1168]": 49145, "[XXXXX311]": 48288, "[XXXXX88]": 48065, "[XXXXX914]": 48891, "[XXXXX1108]": 49085, "[XXXXX466]": 48443, "[XXXXX25]": 48002, "[XXXXX1017]": 48994, "[XXXXX972]": 48949, "[XXXXX942]": 48919, "[XXXXX230]": 48207, "[XXXXX248]": 48225, "[XXXXX197]": 48174, "[XXXXX662]": 48639, "[XXXXX340]": 48317, "[XXXXX1103]": 49080, "[XXXXX8]": 47985, "[XXXXX333]": 48310, "[XXXXX49]": 48026, "[XXXXX902]": 48879, "[XXXXX252]": 48229, "[XXXXX1095]": 49072, "[XXXXX307]": 48284, "[XXXXX4]": 47981, "[XXXXX237]": 48214, "[XXXXX1170]": 49147, "[XXXXX776]": 48753, "[XXXXX897]": 48874, "[XXXXX707]": 48684, "[XXXXX1036]": 49013, "[XXXXX923]": 48900, "[XXXXX416]": 48393, "[XXXXX174]": 48151, "[XXXXX354]": 48331, "[XXXXX365]": 48342, "[XXXXX624]": 48601, "[XXXXX669]": 48646, "[XXXXX883]": 48860, "[XXXXX865]": 48842, "[XXXXX73]": 48050, "[XXXXX360]": 48337, "[XXXXX1164]": 49141, "[XXXXX920]": 48897, "[XXXXX86]": 48063, "[XXXXX37]": 48014, "[XXXXX236]": 48213, "[XXXXX164]": 48141, "[XXXXX1099]": 49076, "[XXXXX537]": 48514, "[XXXXX157]": 48134, "[XXXXX911]": 48888, "[XXXXX208]": 48185, "[XXXXX859]": 48836, "[XXXXX31]": 48008, "[XXXXX415]": 48392, "[XXXXX724]": 48701, "[XXXXX483]": 48460, "[XXXXX988]": 48965, "[XXXXX709]": 48686, "[XXXXX323]": 48300, "[XXXXX393]": 48370, "[XXXXX682]": 48659, "[XXXXX1013]": 48990, "[XXXXX305]": 48282, "[XXXXX453]": 48430, "[XXXXX1081]": 49058, "[XXXXX140]": 48117, "[XXXXX706]": 48683, "[XXXXX997]": 48974, "[XXXXX55]": 48032, "[XXXXX287]": 48264, "[XXXXX1165]": 49142, "[XXXXX201]": 48178, "[XXXXX1044]": 49021, "[XXXXX369]": 48346, "[XXXXX32]": 48009, "[XXXXX475]": 48452, "[XXXXX910]": 48887, "[XXXXX1040]": 49017, "[XXXXX591]": 48568, "[XXXXX895]": 48872, "[XXXXX1019]": 48996, "[XXXXX824]": 48801, "[XXXXX598]": 48575, "[XXXXX985]": 48962, "[XXXXX573]": 48550, "[XXXXX116]": 48093, "[XXXXX296]": 48273, "[XXXXX324]": 48301, "[XXXXX773]": 48750, "[XXXXX184]": 48161, "[XXXXX931]": 48908, "[XXXXX1093]": 49070, "[XXXXX326]": 48303, "[XXXXX465]": 48442, "[XXXXX1024]": 49001, "[XXXXX1104]": 49081, "[XXXXX151]": 48128, "[XXXXX1133]": 49110, "[XXXXX915]": 48892, "[XXXXX846]": 48823, "[XXXXX955]": 48932, "[XXXXX171]": 48148, "[XXXXX1125]": 49102, "[XXXXX1141]": 49118, "[XXXXX121]": 48098, "[XXXXX894]": 48871, "[XXXXX1086]": 49063, "[XXXXX126]": 48103, "[XXXXX469]": 48446, "[XXXXX649]": 48626, "[XXXXX798]": 48775, "[XXXXX877]": 48854, "[XXXXX888]": 48865, "[XXXXX82]": 48059, "[XXXXX1021]": 48998, "[XXXXX715]": 48692, "[XXXXX1]": 47978, "[XXXXX1088]": 49065, "[XXXXX3]": 47980, "[XXXXX705]": 48682, "[XXXXX740]": 48717, "[XXXXX457]": 48434, "[XXXXX721]": 48698, "[XXXXX831]": 48808, "[XXXXX1014]": 48991, "[XXXXX684]": 48661, "[XXXXX317]": 48294, "[XXXXX693]": 48670, "[XXXXX760]": 48737, "[XXXXX160]": 48137, "[XXXXX755]": 48732, "[XXXXX570]": 48547, "[XXXXX60]": 48037, "[XXXXX38]": 48015, "[XXXXX83]": 48060, "[XXXXX556]": 48533, "[XXXXX1069]": 49046, "[XXXXX963]": 48940, "[XXXXX182]": 48159, "[XXXXX93]": 48070, "[XXXXX793]": 48770, "[XXXXX857]": 48834, "[XXXXX260]": 48237, "[XXXXX810]": 48787, "[XXXXX1114]": 49091, "[XXXXX530]": 48507, "[XXXXX874]": 48851, "[XXXXX933]": 48910, "[XXXXX85]": 48062, "[XXXXX56]": 48033, "[XXXXX368]": 48345, "[XXXXX47]": 48024, "[XXXXX725]": 48702, "[XXXXX176]": 48153, "[XXXXX749]": 48726, "[XXXXX211]": 48188, "[XXXXX908]": 48885, "[XXXXX133]": 48110, "[XXXXX921]": 48898, "[XXXXX1058]": 49035, "[XXXXX272]": 48249, "[XXXXX692]": 48669, "[XXXXX868]": 48845, "[XXXXX551]": 48528, "[XXXXX480]": 48457, "[XXXXX309]": 48286, "[XXXXX737]": 48714, "[XXXXX297]": 48274, "[XXXXX1005]": 48982, "[XXXXX632]": 48609, "[XXXXX276]": 48253, "[XXXXX327]": 48304, "[XXXXX441]": 48418, "[XXXXX600]": 48577, "[XXXXX439]": 48416, "[XXXXX1146]": 49123, "[XXXXX547]": 48524, "[XXXXX440]": 48417, "[XXXXX788]": 48765, "[XXXXX435]": 48412, "[XXXXX577]": 48554, "[XXXXX832]": 48809, "[XXXXX100]": 48077, "[XXXXX185]": 48162, "[XXXXX394]": 48371, "[XXXXX1030]": 49007, "[XXXXX809]": 48786, "[XXXXX92]": 48069, "[XXXXX177]": 48154, "[XXXXX702]": 48679, "[XXXXX587]": 48564, "[XXXXX962]": 48939, "[XXXXX279]": 48256, "[XXXXX1018]": 48995, "[XXXXX103]": 48080, "[XXXXX39]": 48016, "[XXXXX219]": 48196, "[XXXXX619]": 48596, "[XXXXX637]": 48614, "[XXXXX901]": 48878, "[XXXXX658]": 48635, "[XXXXX723]": 48700, "[XXXXX1169]": 49146, "[XXXXX518]": 48495, "[XXXXX336]": 48313, "[XXXXX1115]": 49092, "[XXXXX173]": 48150, "[XXXXX657]": 48634, "[XXXXX205]": 48182, "[XXXXX779]": 48756, "[XXXXX806]": 48783, "[XXXXX750]": 48727, "[XXXXX377]": 48354, "[XXXXX168]": 48145, "[XXXXX53]": 48030, "[XXXXX731]": 48708, "[XXXXX284]": 48261, "[XXXXX528]": 48505, "[XXXXX264]": 48241, "[XXXXX579]": 48556, "[XXXXX231]": 48208, "[XXXXX14]": 47991, "[XXXXX505]": 48482, "[XXXXX1174]": 49151, "[XXXXX869]": 48846, "[XXXXX459]": 48436, "[XXXXX255]": 48232, "[XXXXX468]": 48445, "[XXXXX286]": 48263, "[XXXXX111]": 48088, "[XXXXX432]": 48409, "[XXXXX953]": 48930, "[XXXXX516]": 48493, "[XXXXX1121]": 49098, "[XXXXX150]": 48127, "[XXXXX567]": 48544, "[XXXXX956]": 48933, "[XXXXX179]": 48156, "[XXXXX1107]": 49084, "[XXXXX502]": 48479, "[XXXXX42]": 48019, "[XXXXX610]": 48587, "[XXXXX1145]": 49122, "[XXXXX263]": 48240, "[XXXXX351]": 48328, "[XXXXX653]": 48630, "[XXXXX727]": 48704, "[XXXXX6]": 47983, "[XXXXX496]": 48473, "[XXXXX19]": 47996, "[XXXXX617]": 48594, "[XXXXX588]": 48565, "[XXXXX694]": 48671, "[XXXXX372]": 48349, "[XXXXX357]": 48334, "[XXXXX759]": 48736, "[XXXXX813]": 48790, "[XXXXX862]": 48839, "[XXXXX302]": 48279, "[XXXXX428]": 48405, "[XXXXX379]": 48356, "[XXXXX148]": 48125, "[XXXXX646]": 48623, "[XXXXX225]": 48202, "[XXXXX586]": 48563, "[XXXXX1001]": 48978, "[XXXXX858]": 48835, "[XXXXX916]": 48893, "[XXXXX797]": 48774, "[XXXXX1062]": 49039, "[XXXXX873]": 48850, "[XXXXX845]": 48822, "[XXXXX1097]": 49074, "[XXXXX690]": 48667, "[XXXXX508]": 48485, "[XXXXX1079]": 49056, "[XXXXX1130]": 49107, "[XXXXX631]": 48608, "[XXXXX1003]": 48980, "[XXXXX941]": 48918, "[XXXXX867]": 48844, "[XXXXX881]": 48858, "[XXXXX803]": 48780, "[XXXXX840]": 48817, "[XXXXX1148]": 49125, "[XXXXX951]": 48928, "[XXXXX1045]": 49022, "[XXXXX696]": 48673, "[XXXXX791]": 48768, "[XXXXX339]": 48316, "[XXXXX383]": 48360, "[XXXXX27]": 48004, "[XXXXX283]": 48260, "[XXXXX836]": 48813, "[XXXXX156]": 48133, "[XXXXX654]": 48631, "[XXXXX1067]": 49044, "[XXXXX622]": 48599, "[XXXXX560]": 48537, "[XXXXX1077]": 49054, "[XXXXX1134]": 49111, "[XXXXX131]": 48108, "[XXXXX268]": 48245, "[XXXXX251]": 48228, "[XXXXX630]": 48607, "[XXXXX525]": 48502, "[XXXXX48]": 48025, "[XXXXX370]": 48347, "[XXXXX123]": 48100, "[XXXXX515]": 48492, "[XXXXX993]": 48970, "[XXXXX980]": 48957, "[XXXXX523]": 48500, "[XXXXX645]": 48622, "[XXXXX548]": 48525, "[XXXXX538]": 48515, "[XXXXX52]": 48029, "[XXXXX628]": 48605, "[XXXXX876]": 48853, "[XXXXX294]": 48271, "[XXXXX2]": 47979, "[XXXXX109]": 48086, "[XXXXX245]": 48222, "[XXXXX409]": 48386, "[XXXXX273]": 48250, "[XXXXX650]": 48627, "[XXXXX474]": 48451, "[XXXXX1025]": 49002, "[XXXXX433]": 48410, "[XXXXX134]": 48111, "[XXXXX903]": 48880, "[XXXXX257]": 48234, "[XXXXX1140]": 49117, "[XXXXX935]": 48912, "[XXXXX835]": 48812, "[XXXXX270]": 48247, "[XXXXX719]": 48696, "[XXXXX443]": 48420, "[XXXXX1128]": 49105, "[XXXXX627]": 48604, "[XXXXX349]": 48326, "[XXXXX574]": 48551, "[XXXXX1046]": 49023, "[XXXXX1038]": 49015, "[XXXXX142]": 48119, "[XXXXX57]": 48034, "[XXXXX847]": 48824, "[XXXXX429]": 48406, "[XXXXX549]": 48526, "[XXXXX1042]": 49019, "[XXXXX1147]": 49124, "[XXXXX298]": 48275, "[XXXXX1033]": 49010, "[XXXXX240]": 48217, "[XXXXX949]": 48926, "[XXXXX66]": 48043, "[XXXXX155]": 48132, "[XXXXX978]": 48955, "[XXXXX871]": 48848, "[XXXXX476]": 48453, "[XXXXX817]": 48794, "[XXXXX1084]": 49061, "[XXXXX590]": 48567, "[XXXXX10]": 47987, "[XXXXX410]": 48387, "[XXXXX215]": 48192, "[XXXXX479]": 48456, "[XXXXX517]": 48494, "[XXXXX1049]": 49026, "[XXXXX187]": 48164, "[XXXXX904]": 48881, "[XXXXX945]": 48922, "[XXXXX223]": 48200, "[XXXXX154]": 48131, "[XXXXX108]": 48085, "[XXXXX1157]": 49134, "[XXXXX534]": 48511, "[XXXXX1136]": 49113, "[XXXXX312]": 48289, "[XXXXX341]": 48318, "[XXXXX63]": 48040, "[XXXXX730]": 48707, "[XXXXX900]": 48877, "[XXXXX214]": 48191, "[XXXXX532]": 48509, "[XXXXX250]": 48227, "[XXXXX1055]": 49032, "[XXXXX77]": 48054, "[XXXXX926]": 48903, "[XXXXX712]": 48689, "[XXXXX405]": 48382, "[XXXXX741]": 48718, "[XXXXX348]": 48325, "[XXXXX937]": 48914, "[XXXXX229]": 48206, "[XXXXX1070]": 49047, "[XXXXX889]": 48866, "[XXXXX833]": 48810, "[XXXXX929]": 48906, "[XXXXX882]": 48859, "[XXXXX388]": 48365, "[XXXXX425]": 48402, "[XXXXX458]": 48435, "[XXXXX738]": 48715, "[XXXXX676]": 48653, "[XXXXX125]": 48102, "[XXXXX1008]": 48985, "[XXXXX930]": 48907, "[XXXXX638]": 48615, "[XXXXX753]": 48730, "[XXXXX599]": 48576, "[XXXXX729]": 48706, "[XXXXX811]": 48788, "[XXXXX220]": 48197, "[XXXXX805]": 48782, "[XXXXX648]": 48625, "[XXXXX1082]": 49059, "[XXXXX1016]": 48993, "[XXXXX400]": 48377, "[XXXXX1135]": 49112, "[XXXXX761]": 48738, "[XXXXX568]": 48545, "[XXXXX200]": 48177, "[XXXXX644]": 48621, "[XXXXX371]": 48348, "[XXXXX828]": 48805, "[XXXXX1162]": 49139, "[XXXXX490]": 48467, "[XXXXX261]": 48238, "[XXXXX655]": 48632, "[XXXXX210]": 48187, "[XXXXX193]": 48170, "[XXXXX358]": 48335, "[XXXXX939]": 48916, "[XXXXX62]": 48039, "[XXXXX80]": 48057, "[CLS]": 47973, "[XXXXX875]": 48852, "[XXXXX332]": 48309, "[XXXXX17]": 47994, "[XXXXX78]": 48055, "[XXXXX107]": 48084, "[XXXXX207]": 48184, "[XXXXX149]": 48126, "[XXXXX318]": 48295, "[XXXXX884]": 48861, "[XXXXX823]": 48800, "[XXXXX799]": 48776, "[XXXXX139]": 48116, "[XXXXX843]": 48820, "[XXXXX463]": 48440, "[XXXXX770]": 48747, "[XXXXX499]": 48476, "[XXXXX886]": 48863, "[XXXXX906]": 48883, "[XXXXX118]": 48095, "[XXXXX1078]": 49055, "[XXXXX778]": 48755, "[XXXXX495]": 48472, "[XXXXX816]": 48793, "[XXXXX127]": 48104, "[XXXXX1109]": 49086, "[XXXXX402]": 48379, "[XXXXX497]": 48474, "[XXXXX1153]": 49130, "[XXXXX421]": 48398, "[XXXXX1083]": 49060, "[XXXXX885]": 48862, "[XXXXX1031]": 49008, "[XXXXX172]": 48149, "[XXXXX363]": 48340, "[XXXXX837]": 48814, "[XXXXX768]": 48745, "[XXXXX861]": 48838, "[XXXXX830]": 48807, "[XXXXX512]": 48489, "[XXXXX1102]": 49079, "[XXXXX558]": 48535, "[XXXXX472]": 48449, "[XXXXX1006]": 48983, "[XXXXX990]": 48967, "[XXXXX995]": 48972, "[XXXXX954]": 48931, "[XXXXX1057]": 49034, "[XXXXX1127]": 49104, "[XXXXX1052]": 49029, "[XXXXX79]": 48056, "[XXXXX629]": 48606, "[XXXXX1089]": 49066, "[XXXXX1139]": 49116, "[XXXXX905]": 48882, "[XXXXX601]": 48578, "[XXXXX488]": 48465, "[XXXXX34]": 48011, "[XXXXX999]": 48976, "[XXXXX777]": 48754, "[XXXXX593]": 48570, "[XXXXX711]": 48688, "[XXXXX1012]": 48989, "[XXXXX202]": 48179, "[XXXXX615]": 48592, "[XXXXX91]": 48068, "[XXXXX878]": 48855, "[XXXXX221]": 48198, "[XXXXX355]": 48332, "[XXXXX952]": 48929, "[XXXXX819]": 48796, "[XXXXX467]": 48444, "[XXXXX45]": 48022, "[XXXXX666]": 48643, "[XXXXX531]": 48508, "[XXXXX699]": 48676, "[XXXXX501]": 48478, "[XXXXX1150]": 49127, "[XXXXX726]": 48703, "[XXXXX751]": 48728, "[XXXXX376]": 48353, "[XXXXX381]": 48358, "[XXXXX337]": 48314, "[XXXXX612]": 48589, "[XXXXX1161]": 49138, "[XXXXX412]": 48389, "[XXXXX634]": 48611, "[XXXXX189]": 48166, "[XXXXX304]": 48281, "[XXXXX1074]": 49051, "[XXXXX161]": 48138, "[XXXXX75]": 48052, "[XXXXX827]": 48804, "[XXXXX664]": 48641, "[XXXXX970]": 48947, "[XXXXX964]": 48941, "[XXXXX30]": 48007, "[XXXXX390]": 48367, "[XXXXX436]": 48413, "[XXXXX378]": 48355, "[XXXXX362]": 48339, "[XXXXX12]": 47989, "[XXXXX420]": 48397, "[XXXXX301]": 48278, "[XXXXX192]": 48169, "[XXXXX87]": 48064, "[XXXXX766]": 48743, "[XXXXX890]": 48867, "[XXXXX503]": 48480, "[XXXXX1015]": 48992, "[XXXXX438]": 48415, "[XXXXX552]": 48529, "[XXXXX815]": 48792, "[XXXXX128]": 48105, "[XXXXX461]": 48438, "[XXXXX790]": 48767, "[XXXXX685]": 48662, "[XXXXX735]": 48712, "[XXXXX241]": 48218, "[XXXXX137]": 48114, "[XXXXX274]": 48251, "[XXXXX572]": 48549, "[XXXXX981]": 48958, "[XXXXX680]": 48657, "[XXXXX506]": 48483, "[XXXXX767]": 48744, "[XXXXX89]": 48066, "[XXXXX589]": 48566, "[XXXXX316]": 48293, "[XXXXX21]": 47998, "[XXXXX212]": 48189, "[XXXXX143]": 48120, "[XXXXX471]": 48448, "[XXXXX1117]": 49094, "[XXXXX292]": 48269, "[XXXXX105]": 48082, "[XXXXX966]": 48943, "[XXXXX18]": 47995, "[XXXXX796]": 48773, "[XXXXX1023]": 49000, "[XXXXX84]": 48061, "[XXXXX392]": 48369, "[XXXXX661]": 48638, "[XXXXX695]": 48672, "[XXXXX114]": 48091, "[XXXXX20]": 47997, "[XXXXX744]": 48721, "[XXXXX1056]": 49033, "[XXXXX346]": 48323, "[XXXXX238]": 48215, "[XXXXX227]": 48204, "[XXXXX982]": 48959, "[XXXXX829]": 48806, "[XXXXX491]": 48468, "[XXXXX277]": 48254, "[XXXXX462]": 48439, "[XXXXX1111]": 49088, "[XXXXX667]": 48644, "[XXXXX1158]": 49135, "[XXXXX454]": 48431, "[XXXXX917]": 48894, "[XXXXX233]": 48210, "[XXXXX909]": 48886, "[XXXXX395]": 48372, "[XXXXX688]": 48665, "[XXXXX783]": 48760, "[XXXXX851]": 48828, "[XXXXX1154]": 49131, "[XXXXX938]": 48915, "[XXXXX282]": 48259, "[XXXXX545]": 48522, "[XXXXX907]": 48884, "[XXXXX640]": 48617, "[XXXXX153]": 48130, "[XXXXX1171]": 49148, "[XXXXX718]": 48695, "[XXXXX752]": 48729, "[XXXXX786]": 48763, "[XXXXX7]": 47984, "[XXXXX97]": 48074, "[XXXXX258]": 48235, "[XXXXX960]": 48937, "[XXXXX1120]": 49097, "[XXXXX398]": 48375, "[XXXXX1034]": 49011, "[XXXXX994]": 48971, "[XXXXX1160]": 49137, "[XXXXX1027]": 49004, "[XXXXX976]": 48953, "[XXXXX291]": 48268, "[XXXXX68]": 48045, "[XXXXX944]": 48921, "[XXXXX623]": 48600, "[XXXXX800]": 48777, "[XXXXX331]": 48308, "[XXXXX138]": 48115, "[XXXXX555]": 48532, "[XXXXX603]": 48580, "[XXXXX364]": 48341, "[XXXXX204]": 48181, "[XXXXX46]": 48023, "[XXXXX1110]": 49087, "[XXXXX675]": 48652, "[XXXXX203]": 48180, "[XXXXX289]": 48266, "[XXXXX922]": 48899, "[XXXXX651]": 48628, "[XXXXX1087]": 49064, "[XXXXX856]": 48833, "[XXXXX812]": 48789, "[XXXXX973]": 48950, "[XXXXX345]": 48322, "[XXXXX932]": 48909, "[XXXXX957]": 48934, "[XXXXX24]": 48001, "[XXXXX947]": 48924, "[XXXXX335]": 48312, "[XXXXX484]": 48461, "[XXXXX152]": 48129, "[XXXXX158]": 48135, "[XXXXX430]": 48407, "[XXXXX787]": 48764, "[XXXXX342]": 48319, "[XXXXX762]": 48739, "[XXXXX756]": 48733, "[XXXXX434]": 48411, "[XXXXX576]": 48553, "[XXXXX686]": 48663, "[XXXXX710]": 48687, "[XXXXX235]": 48212, "[XXXXX386]": 48363, "[XXXXX374]": 48351, "[XXXXX848]": 48825, "[XXXXX1011]": 48988, "[XXXXX722]": 48699, "[XXXXX979]": 48956, "[XXXXX642]": 48619, "[XXXXX656]": 48633, "[XXXXX849]": 48826, "[XXXXX447]": 48424, "[XXXXX1156]": 49133, "[XXXXX742]": 48719, "[XXXXX850]": 48827, "<pad>": 47975, "[XXXXX925]": 48902, "[XXXXX700]": 48677, "[XXXXX344]": 48321, "[XXXXX487]": 48464, "[XXXXX353]": 48330, "[XXXXX524]": 48501, "[XXXXX544]": 48521, "[XXXXX866]": 48843, "[XXXXX1131]": 49108, "[XXXXX514]": 48491, "[XXXXX940]": 48917, "[XXXXX315]": 48292, "[XXXXX247]": 48224, "[XXXXX249]": 48226, "[XXXXX822]": 48799, "[XXXXX99]": 48076, "[XXXXX758]": 48735, "[XXXXX81]": 48058, "[XXXXX844]": 48821, "[XXXXX113]": 48090, "[XXXXX533]": 48510, "[XXXXX912]": 48889, "[XXXXX330]": 48307, "[XXXXX864]": 48841, "[XXXXX842]": 48819, "[XXXXX595]": 48572, "[XXXXX464]": 48441, "[XXXXX162]": 48139, "[XXXXX659]": 48636, "[XXXXX90]": 48067, "[XXXXX234]": 48211, "[XXXXX373]": 48350, "[XXXXX841]": 48818, "[XXXXX984]": 48961, "[XXXXX1032]": 49009, "[XXXXX1132]": 49109, "[XXXXX513]": 48490, "[XXXXX35]": 48012, "[XXXXX396]": 48373, "[XXXXX69]": 48046, "[XXXXX991]": 48968, "[XXXXX820]": 48797, "[XXXXX112]": 48089, "[XXXXX482]": 48459, "[XXXXX1094]": 49071, "[XXXXX582]": 48559, "[XXXXX444]": 48421, "[XXXXX98]": 48075, "[XXXXX893]": 48870, "[XXXXX106]": 48083, "[XXXXX293]": 48270, "[XXXXX36]": 48013, "[XXXXX996]": 48973, "[XXXXX1028]": 49005, "[XXXXX280]": 48257, "[XXXXX553]": 48530, "[XXXXX569]": 48546, "[XXXXX329]": 48306, "[XXXXX565]": 48542, "[XXXXX739]": 48716, "[XXXXX687]": 48664, "[XXXXX1048]": 49025, "[XXXXX1149]": 49126, "[XXXXX668]": 48645, "[XXXXX188]": 48165, "[XXXXX28]": 48005, "[XXXXX367]": 48344, "[XXXXX971]": 48948, "[XXXXX285]": 48262, "[XXXXX647]": 48624, "[XXXXX206]": 48183, "[XXXXX1129]": 49106, "[XXXXX769]": 48746, "[XXXXX987]": 48964, "[XXXXX855]": 48832, "[XXXXX852]": 48829, "[XXXXX194]": 48171, "[XXXXX1113]": 49090, "[XXXXX578]": 48555, "[XXXXX967]": 48944, "[XXXXX265]": 48242, "[XXXXX300]": 48277, "[XXXXX145]": 48122, "[XXXXX183]": 48160, "[XXXXX129]": 48106, "[XXXXX1090]": 49067, "[XXXXX521]": 48498, "[XXXXX814]": 48791, "[XXXXX1050]": 49027, "[XXXXX175]": 48152, "[XXXXX1020]": 48997, "[XXXXX422]": 48399, "[XXXXX278]": 48255, "[XXXXX714]": 48691, "[XXXXX713]": 48690, "[XXXXX546]": 48523, "[XXXXX1047]": 49024, "[XXXXX191]": 48168, "[XXXXX527]": 48504, "[XXXXX478]": 48455, "[XXXXX310]": 48287, "[XXXXX295]": 48272, "[XXXXX1051]": 49028, "[XXXXX1059]": 49036, "[XXXXX511]": 48488, "[XXXXX218]": 48195, "[XXXXX1106]": 49083, "[XXXXX754]": 48731, "[XXXXX854]": 48831, "[XXXXX913]": 48890, "[XXXXX1080]": 49057, "[XXXXX0]": 47977, "[XXXXX44]": 48021, "[XXXXX1029]": 49006, "[XXXXX424]": 48401, "[XXXXX924]": 48901, "[XXXXX1173]": 49150, "[XXXXX605]": 48582, "[XXXXX919]": 48896, "[XXXXX808]": 48785, "[XXXXX507]": 48484, "[XXXXX11]": 47988, "[XXXXX961]": 48938, "[XXXXX64]": 48041, "[XXXXX1119]": 49096, "[XXXXX473]": 48450, "[XXXXX50]": 48027, "[XXXXX989]": 48966, "[XXXXX413]": 48390, "[XXXXX1163]": 49140, "[XXXXX481]": 48458, "[XXXXX216]": 48193, "[XXXXX708]": 48685, "[XXXXX58]": 48035, "[XXXXX717]": 48694, "[XXXXX494]": 48471, "[XXXXX442]": 48419, "[XXXXX526]": 48503, "[XXXXX789]": 48766, "[XXXXX736]": 48713, "[XXXXX281]": 48258, "[XXXXX571]": 48548, "[XXXXX328]": 48305, "[XXXXX1096]": 49073, "[XXXXX1071]": 49048, "[XXXXX213]": 48190, "[XXXXX620]": 48597, "[XXXXX180]": 48157, "[XXXXX641]": 48618, "[XXXXX1053]": 49030, "[XXXXX585]": 48562, "[XXXXX536]": 48513, "[XXXXX974]": 48951, "[XXXXX407]": 48384, "[XXXXX581]": 48558, "[XXXXX74]": 48051, "[XXXXX614]": 48591, "[XXXXX948]": 48925, "[XXXXX338]": 48315, "[XXXXX1026]": 49003, "[XXXXX743]": 48720, "[XXXXX771]": 48748, "[XXXXX1091]": 49068, "[XXXXX1152]": 49129, "[XXXXX259]": 48236, "[XXXXX16]": 47993, "[XXXXX1068]": 49045, "[XXXXX818]": 48795, "[XXXXX308]": 48285, "[XXXXX144]": 48121, "[XXXXX254]": 48231, "[XXXXX209]": 48186, "[XXXXX288]": 48265, "[XXXXX1101]": 49078, "[XXXXX1112]": 49089, "[XXXXX936]": 48913, "[XXXXX679]": 48656, "[XXXXX1035]": 49012, "[XXXXX382]": 48359, "[XXXXX222]": 48199, "[XXXXX217]": 48194, "[XXXXX96]": 48073, "[XXXXX872]": 48849, "[XXXXX102]": 48079, "[XXXXX266]": 48243, "[XXXXX361]": 48338, "[XXXXX704]": 48681, "[XXXXX319]": 48296, "[XXXXX246]": 48223, "[XXXXX860]": 48837, "[XXXXX166]": 48143, "[XXXXX76]": 48053, "[XXXXX1142]": 49119, "[XXXXX1092]": 49069, "[XXXXX584]": 48561, "[XXXXX299]": 48276, "[XXXXX504]": 48481, "[XXXXX426]": 48403, "[XXXXX500]": 48477, "[XXXXX101]": 48078, "[XXXXX510]": 48487, "[XXXXX701]": 48678, "[XXXXX269]": 48246, "[XXXXX887]": 48864, "[XXXXX411]": 48388, "[XXXXX977]": 48954, "[XXXXX40]": 48017, "[XXXXX95]": 48072, "[XXXXX163]": 48140, "[XXXXX604]": 48581, "[XXXXX198]": 48175, "[XXXXX1076]": 49053, "[XXXXX119]": 48096, "[XXXXX1000]": 48977, "[XXXXX969]": 48946, "[XXXXX1155]": 49132, "[XXXXX389]": 48366, "[XXXXX660]": 48637, "[XXXXX677]": 48654, "[XXXXX1122]": 49099, "[XXXXX267]": 48244, "[XXXXX918]": 48895, "[XXXXX1060]": 49037, "[XXXXX72]": 48049, "[XXXXX122]": 48099, "[XXXXX169]": 48146, "[XXXXX748]": 48725, "[XXXXX43]": 48020, "[XXXXX583]": 48560, "[XXXXX1022]": 48999, "[XXXXX343]": 48320, "[XXXXX470]": 48447, "[XXXXX734]": 48711, "[XXXXX674]": 48651, "[XXXXX1041]": 49018, "[XXXXX65]": 48042, "[XXXXX522]": 48499, "[XXXXX1009]": 48986, "[XXXXX59]": 48036, "[XXXXX1072]": 49049, "[XXXXX838]": 48815, "[XXXXX29]": 48006, "[XXXXX492]": 48469, "[XXXXX1002]": 48979, "[XXXXX898]": 48875, "[XXXXX946]": 48923, "[XXXXX509]": 48486, "[XXXXX745]": 48722, "[XXXXX1105]": 49082, "[XXXXX780]": 48757, "[XXXXX498]": 48475, "[XXXXX557]": 48534, "[XXXXX1166]": 49143, "[XXXXX455]": 48432, "[XXXXX399]": 48376, "[XXXXX1159]": 49136, "[XXXXX592]": 48569, "[XXXXX414]": 48391, "[XXXXX313]": 48290, "[XXXXX639]": 48616, "[XXXXX782]": 48759, "[XXXXX597]": 48574, "[XXXXX764]": 48741, "[XXXXX347]": 48324, "[XXXXX303]": 48280, "[XXXXX262]": 48239, "[XXXXX427]": 48404, "[XXXXX543]": 48520, "[XXXXX387]": 48364, "[XXXXX1007]": 48984, "[XXXXX807]": 48784, "[XXXXX178]": 48155, "[XXXXX115]": 48092, "[XXXXX1004]": 48981, "[XXXXX826]": 48803, "[XXXXX253]": 48230, "[XXXXX839]": 48816, "[XXXXX983]": 48960, "[XXXXX1126]": 49103, "[XXXXX1043]": 49020, "[XXXXX747]": 48724, "[XXXXX765]": 48742, "[XXXXX314]": 48291, "[XXXXX998]": 48975, "[XXXXX104]": 48081, "[XXXXX1138]": 49115, "[XXXXX170]": 48147, "[XXXXX520]": 48497, "[XXXXX652]": 48629, "[XXXXX681]": 48658, "[XXXXX271]": 48248, "[XXXXX15]": 47992, "[XXXXX794]": 48771, "[XXXXX1137]": 49114, "[XXXXX608]": 48585, "[XXXXX934]": 48911, "[XXXXX321]": 48298, "[XXXXX1010]": 48987, "[XXXXX159]": 48136, "[XXXXX643]": 48620, "[XXXXX1124]": 49101, "[XXXXX626]": 48603, "[XXXXX539]": 48516, "[XXXXX243]": 48220}
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["[XXXXX0]", "[XXXXX1]", "[XXXXX2]", "[XXXXX3]", "[XXXXX4]", "[XXXXX5]", "[XXXXX6]", "[XXXXX7]", "[XXXXX8]", "[XXXXX9]", "[XXXXX10]", "[XXXXX11]", "[XXXXX12]", "[XXXXX13]", "[XXXXX14]", "[XXXXX15]", "[XXXXX16]", "[XXXXX17]", "[XXXXX18]", "[XXXXX19]", "[XXXXX20]", "[XXXXX21]", "[XXXXX22]", "[XXXXX23]", "[XXXXX24]", "[XXXXX25]", "[XXXXX26]", "[XXXXX27]", "[XXXXX28]", "[XXXXX29]", "[XXXXX30]", "[XXXXX31]", "[XXXXX32]", "[XXXXX33]", "[XXXXX34]", "[XXXXX35]", "[XXXXX36]", "[XXXXX37]", "[XXXXX38]", "[XXXXX39]", "[XXXXX40]", "[XXXXX41]", "[XXXXX42]", "[XXXXX43]", "[XXXXX44]", "[XXXXX45]", "[XXXXX46]", "[XXXXX47]", "[XXXXX48]", "[XXXXX49]", "[XXXXX50]", "[XXXXX51]", "[XXXXX52]", "[XXXXX53]", "[XXXXX54]", "[XXXXX55]", "[XXXXX56]", "[XXXXX57]", "[XXXXX58]", "[XXXXX59]", "[XXXXX60]", "[XXXXX61]", "[XXXXX62]", "[XXXXX63]", "[XXXXX64]", "[XXXXX65]", "[XXXXX66]", "[XXXXX67]", "[XXXXX68]", "[XXXXX69]", "[XXXXX70]", "[XXXXX71]", "[XXXXX72]", "[XXXXX73]", "[XXXXX74]", "[XXXXX75]", "[XXXXX76]", "[XXXXX77]", "[XXXXX78]", "[XXXXX79]", "[XXXXX80]", "[XXXXX81]", "[XXXXX82]", "[XXXXX83]", "[XXXXX84]", "[XXXXX85]", "[XXXXX86]", "[XXXXX87]", "[XXXXX88]", "[XXXXX89]", "[XXXXX90]", "[XXXXX91]", "[XXXXX92]", "[XXXXX93]", "[XXXXX94]", "[XXXXX95]", "[XXXXX96]", "[XXXXX97]", "[XXXXX98]", "[XXXXX99]", "[XXXXX100]", "[XXXXX101]", "[XXXXX102]", "[XXXXX103]", "[XXXXX104]", "[XXXXX105]", "[XXXXX106]", "[XXXXX107]", "[XXXXX108]", "[XXXXX109]", "[XXXXX110]", "[XXXXX111]", "[XXXXX112]", "[XXXXX113]", "[XXXXX114]", "[XXXXX115]", "[XXXXX116]", "[XXXXX117]", "[XXXXX118]", "[XXXXX119]", "[XXXXX120]", "[XXXXX121]", "[XXXXX122]", "[XXXXX123]", "[XXXXX124]", "[XXXXX125]", "[XXXXX126]", "[XXXXX127]", "[XXXXX128]", "[XXXXX129]", "[XXXXX130]", "[XXXXX131]", "[XXXXX132]", "[XXXXX133]", "[XXXXX134]", "[XXXXX135]", "[XXXXX136]", "[XXXXX137]", "[XXXXX138]", "[XXXXX139]", "[XXXXX140]", "[XXXXX141]", "[XXXXX142]", "[XXXXX143]", "[XXXXX144]", "[XXXXX145]", "[XXXXX146]", "[XXXXX147]", "[XXXXX148]", "[XXXXX149]", "[XXXXX150]", "[XXXXX151]", "[XXXXX152]", "[XXXXX153]", "[XXXXX154]", "[XXXXX155]", "[XXXXX156]", "[XXXXX157]", "[XXXXX158]", "[XXXXX159]", "[XXXXX160]", "[XXXXX161]", "[XXXXX162]", "[XXXXX163]", "[XXXXX164]", "[XXXXX165]", "[XXXXX166]", "[XXXXX167]", "[XXXXX168]", "[XXXXX169]", "[XXXXX170]", "[XXXXX171]", "[XXXXX172]", "[XXXXX173]", "[XXXXX174]", "[XXXXX175]", "[XXXXX176]", "[XXXXX177]", "[XXXXX178]", "[XXXXX179]", "[XXXXX180]", "[XXXXX181]", "[XXXXX182]", "[XXXXX183]", "[XXXXX184]", "[XXXXX185]", "[XXXXX186]", "[XXXXX187]", "[XXXXX188]", "[XXXXX189]", "[XXXXX190]", "[XXXXX191]", "[XXXXX192]", "[XXXXX193]", "[XXXXX194]", "[XXXXX195]", "[XXXXX196]", "[XXXXX197]", "[XXXXX198]", "[XXXXX199]", "[XXXXX200]", "[XXXXX201]", "[XXXXX202]", "[XXXXX203]", "[XXXXX204]", "[XXXXX205]", "[XXXXX206]", "[XXXXX207]", "[XXXXX208]", "[XXXXX209]", "[XXXXX210]", "[XXXXX211]", "[XXXXX212]", "[XXXXX213]", "[XXXXX214]", "[XXXXX215]", "[XXXXX216]", "[XXXXX217]", "[XXXXX218]", "[XXXXX219]", "[XXXXX220]", "[XXXXX221]", "[XXXXX222]", "[XXXXX223]", "[XXXXX224]", "[XXXXX225]", "[XXXXX226]", "[XXXXX227]", "[XXXXX228]", "[XXXXX229]", "[XXXXX230]", "[XXXXX231]", "[XXXXX232]", "[XXXXX233]", "[XXXXX234]", "[XXXXX235]", "[XXXXX236]", "[XXXXX237]", "[XXXXX238]", "[XXXXX239]", "[XXXXX240]", "[XXXXX241]", "[XXXXX242]", "[XXXXX243]", "[XXXXX244]", "[XXXXX245]", "[XXXXX246]", "[XXXXX247]", "[XXXXX248]", "[XXXXX249]", "[XXXXX250]", "[XXXXX251]", "[XXXXX252]", "[XXXXX253]", "[XXXXX254]", "[XXXXX255]", "[XXXXX256]", "[XXXXX257]", "[XXXXX258]", "[XXXXX259]", "[XXXXX260]", "[XXXXX261]", "[XXXXX262]", "[XXXXX263]", "[XXXXX264]", "[XXXXX265]", "[XXXXX266]", "[XXXXX267]", "[XXXXX268]", "[XXXXX269]", "[XXXXX270]", "[XXXXX271]", "[XXXXX272]", "[XXXXX273]", "[XXXXX274]", "[XXXXX275]", "[XXXXX276]", "[XXXXX277]", "[XXXXX278]", "[XXXXX279]", "[XXXXX280]", "[XXXXX281]", "[XXXXX282]", "[XXXXX283]", "[XXXXX284]", "[XXXXX285]", "[XXXXX286]", "[XXXXX287]", "[XXXXX288]", "[XXXXX289]", "[XXXXX290]", "[XXXXX291]", "[XXXXX292]", "[XXXXX293]", "[XXXXX294]", "[XXXXX295]", "[XXXXX296]", "[XXXXX297]", "[XXXXX298]", "[XXXXX299]", "[XXXXX300]", "[XXXXX301]", "[XXXXX302]", "[XXXXX303]", "[XXXXX304]", "[XXXXX305]", "[XXXXX306]", "[XXXXX307]", "[XXXXX308]", "[XXXXX309]", "[XXXXX310]", "[XXXXX311]", "[XXXXX312]", "[XXXXX313]", "[XXXXX314]", "[XXXXX315]", "[XXXXX316]", "[XXXXX317]", "[XXXXX318]", "[XXXXX319]", "[XXXXX320]", "[XXXXX321]", "[XXXXX322]", "[XXXXX323]", "[XXXXX324]", "[XXXXX325]", "[XXXXX326]", "[XXXXX327]", "[XXXXX328]", "[XXXXX329]", "[XXXXX330]", "[XXXXX331]", "[XXXXX332]", "[XXXXX333]", "[XXXXX334]", "[XXXXX335]", "[XXXXX336]", "[XXXXX337]", "[XXXXX338]", "[XXXXX339]", "[XXXXX340]", "[XXXXX341]", "[XXXXX342]", "[XXXXX343]", "[XXXXX344]", "[XXXXX345]", "[XXXXX346]", "[XXXXX347]", "[XXXXX348]", "[XXXXX349]", "[XXXXX350]", "[XXXXX351]", "[XXXXX352]", "[XXXXX353]", "[XXXXX354]", "[XXXXX355]", "[XXXXX356]", "[XXXXX357]", "[XXXXX358]", "[XXXXX359]", "[XXXXX360]", "[XXXXX361]", "[XXXXX362]", "[XXXXX363]", "[XXXXX364]", "[XXXXX365]", "[XXXXX366]", "[XXXXX367]", "[XXXXX368]", "[XXXXX369]", "[XXXXX370]", "[XXXXX371]", "[XXXXX372]", "[XXXXX373]", "[XXXXX374]", "[XXXXX375]", "[XXXXX376]", "[XXXXX377]", "[XXXXX378]", "[XXXXX379]", "[XXXXX380]", "[XXXXX381]", "[XXXXX382]", "[XXXXX383]", "[XXXXX384]", "[XXXXX385]", "[XXXXX386]", "[XXXXX387]", "[XXXXX388]", "[XXXXX389]", "[XXXXX390]", "[XXXXX391]", "[XXXXX392]", "[XXXXX393]", "[XXXXX394]", "[XXXXX395]", "[XXXXX396]", "[XXXXX397]", "[XXXXX398]", "[XXXXX399]", "[XXXXX400]", "[XXXXX401]", "[XXXXX402]", "[XXXXX403]", "[XXXXX404]", "[XXXXX405]", "[XXXXX406]", "[XXXXX407]", "[XXXXX408]", "[XXXXX409]", "[XXXXX410]", "[XXXXX411]", "[XXXXX412]", "[XXXXX413]", "[XXXXX414]", "[XXXXX415]", "[XXXXX416]", "[XXXXX417]", "[XXXXX418]", "[XXXXX419]", "[XXXXX420]", "[XXXXX421]", "[XXXXX422]", "[XXXXX423]", "[XXXXX424]", "[XXXXX425]", "[XXXXX426]", "[XXXXX427]", "[XXXXX428]", "[XXXXX429]", "[XXXXX430]", "[XXXXX431]", "[XXXXX432]", "[XXXXX433]", "[XXXXX434]", "[XXXXX435]", "[XXXXX436]", "[XXXXX437]", "[XXXXX438]", "[XXXXX439]", "[XXXXX440]", "[XXXXX441]", "[XXXXX442]", "[XXXXX443]", "[XXXXX444]", "[XXXXX445]", "[XXXXX446]", "[XXXXX447]", "[XXXXX448]", "[XXXXX449]", "[XXXXX450]", "[XXXXX451]", "[XXXXX452]", "[XXXXX453]", "[XXXXX454]", "[XXXXX455]", "[XXXXX456]", "[XXXXX457]", "[XXXXX458]", "[XXXXX459]", "[XXXXX460]", "[XXXXX461]", "[XXXXX462]", "[XXXXX463]", "[XXXXX464]", "[XXXXX465]", "[XXXXX466]", "[XXXXX467]", "[XXXXX468]", "[XXXXX469]", "[XXXXX470]", "[XXXXX471]", "[XXXXX472]", "[XXXXX473]", "[XXXXX474]", "[XXXXX475]", "[XXXXX476]", "[XXXXX477]", "[XXXXX478]", "[XXXXX479]", "[XXXXX480]", "[XXXXX481]", "[XXXXX482]", "[XXXXX483]", "[XXXXX484]", "[XXXXX485]", "[XXXXX486]", "[XXXXX487]", "[XXXXX488]", "[XXXXX489]", "[XXXXX490]", "[XXXXX491]", "[XXXXX492]", "[XXXXX493]", "[XXXXX494]", "[XXXXX495]", "[XXXXX496]", "[XXXXX497]", "[XXXXX498]", "[XXXXX499]", "[XXXXX500]", "[XXXXX501]", "[XXXXX502]", "[XXXXX503]", "[XXXXX504]", "[XXXXX505]", "[XXXXX506]", "[XXXXX507]", "[XXXXX508]", "[XXXXX509]", "[XXXXX510]", "[XXXXX511]", "[XXXXX512]", "[XXXXX513]", "[XXXXX514]", "[XXXXX515]", "[XXXXX516]", "[XXXXX517]", "[XXXXX518]", "[XXXXX519]", "[XXXXX520]", "[XXXXX521]", "[XXXXX522]", "[XXXXX523]", "[XXXXX524]", "[XXXXX525]", "[XXXXX526]", "[XXXXX527]", "[XXXXX528]", "[XXXXX529]", "[XXXXX530]", "[XXXXX531]", "[XXXXX532]", "[XXXXX533]", "[XXXXX534]", "[XXXXX535]", "[XXXXX536]", "[XXXXX537]", "[XXXXX538]", "[XXXXX539]", "[XXXXX540]", "[XXXXX541]", "[XXXXX542]", "[XXXXX543]", "[XXXXX544]", "[XXXXX545]", "[XXXXX546]", "[XXXXX547]", "[XXXXX548]", "[XXXXX549]", "[XXXXX550]", "[XXXXX551]", "[XXXXX552]", "[XXXXX553]", "[XXXXX554]", "[XXXXX555]", "[XXXXX556]", "[XXXXX557]", "[XXXXX558]", "[XXXXX559]", "[XXXXX560]", "[XXXXX561]", "[XXXXX562]", "[XXXXX563]", "[XXXXX564]", "[XXXXX565]", "[XXXXX566]", "[XXXXX567]", "[XXXXX568]", "[XXXXX569]", "[XXXXX570]", "[XXXXX571]", "[XXXXX572]", "[XXXXX573]", "[XXXXX574]", "[XXXXX575]", "[XXXXX576]", "[XXXXX577]", "[XXXXX578]", "[XXXXX579]", "[XXXXX580]", "[XXXXX581]", "[XXXXX582]", "[XXXXX583]", "[XXXXX584]", "[XXXXX585]", "[XXXXX586]", "[XXXXX587]", "[XXXXX588]", "[XXXXX589]", "[XXXXX590]", "[XXXXX591]", "[XXXXX592]", "[XXXXX593]", "[XXXXX594]", "[XXXXX595]", "[XXXXX596]", "[XXXXX597]", "[XXXXX598]", "[XXXXX599]", "[XXXXX600]", "[XXXXX601]", "[XXXXX602]", "[XXXXX603]", "[XXXXX604]", "[XXXXX605]", "[XXXXX606]", "[XXXXX607]", "[XXXXX608]", "[XXXXX609]", "[XXXXX610]", "[XXXXX611]", "[XXXXX612]", "[XXXXX613]", "[XXXXX614]", "[XXXXX615]", "[XXXXX616]", "[XXXXX617]", "[XXXXX618]", "[XXXXX619]", "[XXXXX620]", "[XXXXX621]", "[XXXXX622]", "[XXXXX623]", "[XXXXX624]", "[XXXXX625]", "[XXXXX626]", "[XXXXX627]", "[XXXXX628]", "[XXXXX629]", "[XXXXX630]", "[XXXXX631]", "[XXXXX632]", "[XXXXX633]", "[XXXXX634]", "[XXXXX635]", "[XXXXX636]", "[XXXXX637]", "[XXXXX638]", "[XXXXX639]", "[XXXXX640]", "[XXXXX641]", "[XXXXX642]", "[XXXXX643]", "[XXXXX644]", "[XXXXX645]", "[XXXXX646]", "[XXXXX647]", "[XXXXX648]", "[XXXXX649]", "[XXXXX650]", "[XXXXX651]", "[XXXXX652]", "[XXXXX653]", "[XXXXX654]", "[XXXXX655]", "[XXXXX656]", "[XXXXX657]", "[XXXXX658]", "[XXXXX659]", "[XXXXX660]", "[XXXXX661]", "[XXXXX662]", "[XXXXX663]", "[XXXXX664]", "[XXXXX665]", "[XXXXX666]", "[XXXXX667]", "[XXXXX668]", "[XXXXX669]", "[XXXXX670]", "[XXXXX671]", "[XXXXX672]", "[XXXXX673]", "[XXXXX674]", "[XXXXX675]", "[XXXXX676]", "[XXXXX677]", "[XXXXX678]", "[XXXXX679]", "[XXXXX680]", "[XXXXX681]", "[XXXXX682]", "[XXXXX683]", "[XXXXX684]", "[XXXXX685]", "[XXXXX686]", "[XXXXX687]", "[XXXXX688]", "[XXXXX689]", "[XXXXX690]", "[XXXXX691]", "[XXXXX692]", "[XXXXX693]", "[XXXXX694]", "[XXXXX695]", "[XXXXX696]", "[XXXXX697]", "[XXXXX698]", "[XXXXX699]", "[XXXXX700]", "[XXXXX701]", "[XXXXX702]", "[XXXXX703]", "[XXXXX704]", "[XXXXX705]", "[XXXXX706]", "[XXXXX707]", "[XXXXX708]", "[XXXXX709]", "[XXXXX710]", "[XXXXX711]", "[XXXXX712]", "[XXXXX713]", "[XXXXX714]", "[XXXXX715]", "[XXXXX716]", "[XXXXX717]", "[XXXXX718]", "[XXXXX719]", "[XXXXX720]", "[XXXXX721]", "[XXXXX722]", "[XXXXX723]", "[XXXXX724]", "[XXXXX725]", "[XXXXX726]", "[XXXXX727]", "[XXXXX728]", "[XXXXX729]", "[XXXXX730]", "[XXXXX731]", "[XXXXX732]", "[XXXXX733]", "[XXXXX734]", "[XXXXX735]", "[XXXXX736]", "[XXXXX737]", "[XXXXX738]", "[XXXXX739]", "[XXXXX740]", "[XXXXX741]", "[XXXXX742]", "[XXXXX743]", "[XXXXX744]", "[XXXXX745]", "[XXXXX746]", "[XXXXX747]", "[XXXXX748]", "[XXXXX749]", "[XXXXX750]", "[XXXXX751]", "[XXXXX752]", "[XXXXX753]", "[XXXXX754]", "[XXXXX755]", "[XXXXX756]", "[XXXXX757]", "[XXXXX758]", "[XXXXX759]", "[XXXXX760]", "[XXXXX761]", "[XXXXX762]", "[XXXXX763]", "[XXXXX764]", "[XXXXX765]", "[XXXXX766]", "[XXXXX767]", "[XXXXX768]", "[XXXXX769]", "[XXXXX770]", "[XXXXX771]", "[XXXXX772]", "[XXXXX773]", "[XXXXX774]", "[XXXXX775]", "[XXXXX776]", "[XXXXX777]", "[XXXXX778]", "[XXXXX779]", "[XXXXX780]", "[XXXXX781]", "[XXXXX782]", "[XXXXX783]", "[XXXXX784]", "[XXXXX785]", "[XXXXX786]", "[XXXXX787]", "[XXXXX788]", "[XXXXX789]", "[XXXXX790]", "[XXXXX791]", "[XXXXX792]", "[XXXXX793]", "[XXXXX794]", "[XXXXX795]", "[XXXXX796]", "[XXXXX797]", "[XXXXX798]", "[XXXXX799]", "[XXXXX800]", "[XXXXX801]", "[XXXXX802]", "[XXXXX803]", "[XXXXX804]", "[XXXXX805]", "[XXXXX806]", "[XXXXX807]", "[XXXXX808]", "[XXXXX809]", "[XXXXX810]", "[XXXXX811]", "[XXXXX812]", "[XXXXX813]", "[XXXXX814]", "[XXXXX815]", "[XXXXX816]", "[XXXXX817]", "[XXXXX818]", "[XXXXX819]", "[XXXXX820]", "[XXXXX821]", "[XXXXX822]", "[XXXXX823]", "[XXXXX824]", "[XXXXX825]", "[XXXXX826]", "[XXXXX827]", "[XXXXX828]", "[XXXXX829]", "[XXXXX830]", "[XXXXX831]", "[XXXXX832]", "[XXXXX833]", "[XXXXX834]", "[XXXXX835]", "[XXXXX836]", "[XXXXX837]", "[XXXXX838]", "[XXXXX839]", "[XXXXX840]", "[XXXXX841]", "[XXXXX842]", "[XXXXX843]", "[XXXXX844]", "[XXXXX845]", "[XXXXX846]", "[XXXXX847]", "[XXXXX848]", "[XXXXX849]", "[XXXXX850]", "[XXXXX851]", "[XXXXX852]", "[XXXXX853]", "[XXXXX854]", "[XXXXX855]", "[XXXXX856]", "[XXXXX857]", "[XXXXX858]", "[XXXXX859]", "[XXXXX860]", "[XXXXX861]", "[XXXXX862]", "[XXXXX863]", "[XXXXX864]", "[XXXXX865]", "[XXXXX866]", "[XXXXX867]", "[XXXXX868]", "[XXXXX869]", "[XXXXX870]", "[XXXXX871]", "[XXXXX872]", "[XXXXX873]", "[XXXXX874]", "[XXXXX875]", "[XXXXX876]", "[XXXXX877]", "[XXXXX878]", "[XXXXX879]", "[XXXXX880]", "[XXXXX881]", "[XXXXX882]", "[XXXXX883]", "[XXXXX884]", "[XXXXX885]", "[XXXXX886]", "[XXXXX887]", "[XXXXX888]", "[XXXXX889]", "[XXXXX890]", "[XXXXX891]", "[XXXXX892]", "[XXXXX893]", "[XXXXX894]", "[XXXXX895]", "[XXXXX896]", "[XXXXX897]", "[XXXXX898]", "[XXXXX899]", "[XXXXX900]", "[XXXXX901]", "[XXXXX902]", "[XXXXX903]", "[XXXXX904]", "[XXXXX905]", "[XXXXX906]", "[XXXXX907]", "[XXXXX908]", "[XXXXX909]", "[XXXXX910]", "[XXXXX911]", "[XXXXX912]", "[XXXXX913]", "[XXXXX914]", "[XXXXX915]", "[XXXXX916]", "[XXXXX917]", "[XXXXX918]", "[XXXXX919]", "[XXXXX920]", "[XXXXX921]", "[XXXXX922]", "[XXXXX923]", "[XXXXX924]", "[XXXXX925]", "[XXXXX926]", "[XXXXX927]", "[XXXXX928]", "[XXXXX929]", "[XXXXX930]", "[XXXXX931]", "[XXXXX932]", "[XXXXX933]", "[XXXXX934]", "[XXXXX935]", "[XXXXX936]", "[XXXXX937]", "[XXXXX938]", "[XXXXX939]", "[XXXXX940]", "[XXXXX941]", "[XXXXX942]", "[XXXXX943]", "[XXXXX944]", "[XXXXX945]", "[XXXXX946]", "[XXXXX947]", "[XXXXX948]", "[XXXXX949]", "[XXXXX950]", "[XXXXX951]", "[XXXXX952]", "[XXXXX953]", "[XXXXX954]", "[XXXXX955]", "[XXXXX956]", "[XXXXX957]", "[XXXXX958]", "[XXXXX959]", "[XXXXX960]", "[XXXXX961]", "[XXXXX962]", "[XXXXX963]", "[XXXXX964]", "[XXXXX965]", "[XXXXX966]", "[XXXXX967]", "[XXXXX968]", "[XXXXX969]", "[XXXXX970]", "[XXXXX971]", "[XXXXX972]", "[XXXXX973]", "[XXXXX974]", "[XXXXX975]", "[XXXXX976]", "[XXXXX977]", "[XXXXX978]", "[XXXXX979]", "[XXXXX980]", "[XXXXX981]", "[XXXXX982]", "[XXXXX983]", "[XXXXX984]", "[XXXXX985]", "[XXXXX986]", "[XXXXX987]", "[XXXXX988]", "[XXXXX989]", "[XXXXX990]", "[XXXXX991]", "[XXXXX992]", "[XXXXX993]", "[XXXXX994]", "[XXXXX995]", "[XXXXX996]", "[XXXXX997]", "[XXXXX998]", "[XXXXX999]", "[XXXXX1000]", "[XXXXX1001]", "[XXXXX1002]", "[XXXXX1003]", "[XXXXX1004]", "[XXXXX1005]", "[XXXXX1006]", "[XXXXX1007]", "[XXXXX1008]", "[XXXXX1009]", "[XXXXX1010]", "[XXXXX1011]", "[XXXXX1012]", "[XXXXX1013]", "[XXXXX1014]", "[XXXXX1015]", "[XXXXX1016]", "[XXXXX1017]", "[XXXXX1018]", "[XXXXX1019]", "[XXXXX1020]", "[XXXXX1021]", "[XXXXX1022]", "[XXXXX1023]", "[XXXXX1024]", "[XXXXX1025]", "[XXXXX1026]", "[XXXXX1027]", "[XXXXX1028]", "[XXXXX1029]", "[XXXXX1030]", "[XXXXX1031]", "[XXXXX1032]", "[XXXXX1033]", "[XXXXX1034]", "[XXXXX1035]", "[XXXXX1036]", "[XXXXX1037]", "[XXXXX1038]", "[XXXXX1039]", "[XXXXX1040]", "[XXXXX1041]", "[XXXXX1042]", "[XXXXX1043]", "[XXXXX1044]", "[XXXXX1045]", "[XXXXX1046]", "[XXXXX1047]", "[XXXXX1048]", "[XXXXX1049]", "[XXXXX1050]", "[XXXXX1051]", "[XXXXX1052]", "[XXXXX1053]", "[XXXXX1054]", "[XXXXX1055]", "[XXXXX1056]", "[XXXXX1057]", "[XXXXX1058]", "[XXXXX1059]", "[XXXXX1060]", "[XXXXX1061]", "[XXXXX1062]", "[XXXXX1063]", "[XXXXX1064]", "[XXXXX1065]", "[XXXXX1066]", "[XXXXX1067]", "[XXXXX1068]", "[XXXXX1069]", "[XXXXX1070]", "[XXXXX1071]", "[XXXXX1072]", "[XXXXX1073]", "[XXXXX1074]", "[XXXXX1075]", "[XXXXX1076]", "[XXXXX1077]", "[XXXXX1078]", "[XXXXX1079]", "[XXXXX1080]", "[XXXXX1081]", "[XXXXX1082]", "[XXXXX1083]", "[XXXXX1084]", "[XXXXX1085]", "[XXXXX1086]", "[XXXXX1087]", "[XXXXX1088]", "[XXXXX1089]", "[XXXXX1090]", "[XXXXX1091]", "[XXXXX1092]", "[XXXXX1093]", "[XXXXX1094]", "[XXXXX1095]", "[XXXXX1096]", "[XXXXX1097]", "[XXXXX1098]", "[XXXXX1099]", "[XXXXX1100]", "[XXXXX1101]", "[XXXXX1102]", "[XXXXX1103]", "[XXXXX1104]", "[XXXXX1105]", "[XXXXX1106]", "[XXXXX1107]", "[XXXXX1108]", "[XXXXX1109]", "[XXXXX1110]", "[XXXXX1111]", "[XXXXX1112]", "[XXXXX1113]", "[XXXXX1114]", "[XXXXX1115]", "[XXXXX1116]", "[XXXXX1117]", "[XXXXX1118]", "[XXXXX1119]", "[XXXXX1120]", "[XXXXX1121]", "[XXXXX1122]", "[XXXXX1123]", "[XXXXX1124]", "[XXXXX1125]", "[XXXXX1126]", "[XXXXX1127]", "[XXXXX1128]", "[XXXXX1129]", "[XXXXX1130]", "[XXXXX1131]", "[XXXXX1132]", "[XXXXX1133]", "[XXXXX1134]", "[XXXXX1135]", "[XXXXX1136]", "[XXXXX1137]", "[XXXXX1138]", "[XXXXX1139]", "[XXXXX1140]", "[XXXXX1141]", "[XXXXX1142]", "[XXXXX1143]", "[XXXXX1144]", "[XXXXX1145]", "[XXXXX1146]", "[XXXXX1147]", "[XXXXX1148]", "[XXXXX1149]", "[XXXXX1150]", "[XXXXX1151]", "[XXXXX1152]", "[XXXXX1153]", "[XXXXX1154]", "[XXXXX1155]", "[XXXXX1156]", "[XXXXX1157]", "[XXXXX1158]", "[XXXXX1159]", "[XXXXX1160]", "[XXXXX1161]", "[XXXXX1162]", "[XXXXX1163]", "[XXXXX1164]", "[XXXXX1165]", "[XXXXX1166]", "[XXXXX1167]", "[XXXXX1168]", "[XXXXX1169]", "[XXXXX1170]", "[XXXXX1171]", "[XXXXX1172]", "[XXXXX1173]", "[XXXXX1174]"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0b8bbe5eb0bfa1b585a700773a1e4b978c4753a0266b1ad979bd0afa2f4e42
3
+ size 1018482
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "name_or_path": "models/5mb/zsm_latn_5mb", "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "models/5mb/zsm_latn_5mb/special_tokens_map.json", "tokenizer_class": "AlbertTokenizer"}