goldfish-models commited on
Commit
1c9f4db
1 Parent(s): 76e0786

Upload lub_latn_5mb tokenizer.

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[XXXXX73]": 42039, "[XXXXX154]": 42120, "[XXXXX175]": 42141, "[XXXXX800]": 42766, "[XXXXX906]": 42872, "[XXXXX921]": 42887, "[XXXXX390]": 42356, "[XXXXX875]": 42841, "[XXXXX453]": 42419, "[XXXXX807]": 42773, "[XXXXX948]": 42914, "[XXXXX854]": 42820, "[XXXXX1012]": 42978, "[XXXXX750]": 42716, "[XXXXX892]": 42858, "[XXXXX203]": 42169, "[XXXXX508]": 42474, "[XXXXX376]": 42342, "[XXXXX325]": 42291, "[XXXXX190]": 42156, "[XXXXX177]": 42143, "[XXXXX922]": 42888, "[XXXXX358]": 42324, "[XXXXX678]": 42644, "[XXXXX1018]": 42984, "[XXXXX974]": 42940, "[XXXXX233]": 42199, "[XXXXX323]": 42289, "[XXXXX747]": 42713, "[XXXXX513]": 42479, "[XXXXX186]": 42152, "[XXXXX301]": 42267, "[XXXXX441]": 42407, "[XXXXX489]": 42455, "[XXXXX133]": 42099, "[XXXXX285]": 42251, "[XXXXX552]": 42518, "[XXXXX878]": 42844, "[XXXXX692]": 42658, "[XXXXX67]": 42033, "[XXXXX736]": 42702, "[XXXXX642]": 42608, "[XXXXX766]": 42732, "[XXXXX294]": 42260, "[XXXXX159]": 42125, "[XXXXX837]": 42803, "[XXXXX216]": 42182, "[XXXXX858]": 42824, "[XXXXX435]": 42401, "[XXXXX1001]": 42967, "[XXXXX578]": 42544, "[XXXXX1017]": 42983, "[XXXXX1026]": 42992, "[XXXXX281]": 42247, "[XXXXX877]": 42843, "[XXXXX606]": 42572, "[XXXXX798]": 42764, "[XXXXX57]": 42023, "[XXXXX197]": 42163, "[XXXXX507]": 42473, "[XXXXX466]": 42432, "[XXXXX644]": 42610, "[XXXXX81]": 42047, "[XXXXX343]": 42309, "[XXXXX613]": 42579, "[XXXXX530]": 42496, "[XXXXX964]": 42930, "[XXXXX78]": 42044, "[XXXXX707]": 42673, "[XXXXX509]": 42475, "[XXXXX161]": 42127, "[XXXXX732]": 42698, "[XXXXX809]": 42775, "[XXXXX354]": 42320, "[XXXXX848]": 42814, "[XXXXX1020]": 42986, "[XXXXX590]": 42556, "[XXXXX1006]": 42972, "[XXXXX840]": 42806, "[XXXXX264]": 42230, "[XXXXX611]": 42577, "[XXXXX702]": 42668, "[XXXXX767]": 42733, "[XXXXX117]": 42083, "[XXXXX372]": 42338, "[XXXXX420]": 42386, "[XXXXX185]": 42151, "[XXXXX431]": 42397, "[XXXXX748]": 42714, "[XXXXX867]": 42833, "[XXXXX1033]": 42999, "[XXXXX585]": 42551, "[XXXXX1007]": 42973, "[XXXXX96]": 42062, "[XXXXX908]": 42874, "[XXXXX405]": 42371, "[XXXXX497]": 42463, "[XXXXX520]": 42486, "[XXXXX498]": 42464, "[XXXXX1039]": 43005, "[XXXXX581]": 42547, "[XXXXX744]": 42710, "[XXXXX913]": 42879, "[XXXXX345]": 42311, "[XXXXX659]": 42625, "[XXXXX80]": 42046, "[XXXXX244]": 42210, "[XXXXX648]": 42614, "[XXXXX776]": 42742, "[XXXXX10]": 41976, "[XXXXX676]": 42642, "[XXXXX607]": 42573, "[SEP]": 41963, "[XXXXX683]": 42649, "[XXXXX677]": 42643, "[XXXXX865]": 42831, "[XXXXX760]": 42726, "[XXXXX444]": 42410, "[XXXXX350]": 42316, "[XXXXX272]": 42238, "[XXXXX774]": 42740, "[XXXXX645]": 42611, "[XXXXX560]": 42526, "[XXXXX211]": 42177, "[XXXXX632]": 42598, "[XXXXX533]": 42499, "[XXXXX629]": 42595, "[XXXXX667]": 42633, "[XXXXX1009]": 42975, "[XXXXX936]": 42902, "[XXXXX269]": 42235, "[XXXXX872]": 42838, "[XXXXX490]": 42456, "[XXXXX995]": 42961, "[XXXXX939]": 42905, "[XXXXX517]": 42483, "[XXXXX44]": 42010, "[XXXXX832]": 42798, "[XXXXX362]": 42328, "[XXXXX456]": 42422, "[XXXXX375]": 42341, "[XXXXX917]": 42883, "[XXXXX321]": 42287, "[XXXXX715]": 42681, "[XXXXX423]": 42389, "[XXXXX932]": 42898, "[XXXXX970]": 42936, "[XXXXX149]": 42115, "[XXXXX357]": 42323, "[XXXXX1040]": 43006, "[XXXXX587]": 42553, "[XXXXX637]": 42603, "[XXXXX778]": 42744, "[XXXXX930]": 42896, "[XXXXX1023]": 42989, "[XXXXX666]": 42632, "[XXXXX157]": 42123, "[XXXXX811]": 42777, "[XXXXX304]": 42270, "[XXXXX905]": 42871, "[XXXXX494]": 42460, "[XXXXX168]": 42134, "[XXXXX931]": 42897, "[XXXXX813]": 42779, "[XXXXX227]": 42193, "[XXXXX262]": 42228, "[XXXXX368]": 42334, "[XXXXX783]": 42749, "[XXXXX882]": 42848, "[XXXXX568]": 42534, "[XXXXX820]": 42786, "[XXXXX9]": 41975, "[XXXXX315]": 42281, "[XXXXX675]": 42641, "[XXXXX705]": 42671, "[XXXXX639]": 42605, "[XXXXX20]": 41986, "[XXXXX205]": 42171, "[XXXXX404]": 42370, "[XXXXX259]": 42225, "[XXXXX395]": 42361, "[XXXXX785]": 42751, "[XXXXX495]": 42461, "[XXXXX823]": 42789, "[XXXXX105]": 42071, "[XXXXX241]": 42207, "[XXXXX215]": 42181, "[XXXXX612]": 42578, "[XXXXX210]": 42176, "[XXXXX179]": 42145, "[XXXXX18]": 41984, "[XXXXX225]": 42191, "[XXXXX787]": 42753, "[XXXXX88]": 42054, "[XXXXX638]": 42604, "[XXXXX226]": 42192, "[XXXXX261]": 42227, "[XXXXX690]": 42656, "[XXXXX112]": 42078, "[XXXXX359]": 42325, "[XXXXX745]": 42711, "[XXXXX119]": 42085, "[XXXXX544]": 42510, "[XXXXX674]": 42640, "[XXXXX531]": 42497, "[XXXXX483]": 42449, "[XXXXX77]": 42043, "[XXXXX839]": 42805, "[XXXXX554]": 42520, "[XXXXX984]": 42950, "[XXXXX597]": 42563, "[XXXXX1010]": 42976, "[XXXXX739]": 42705, "[XXXXX726]": 42692, "[MASK]": 41965, "[XXXXX957]": 42923, "[XXXXX59]": 42025, "[XXXXX991]": 42957, "[XXXXX868]": 42834, "[XXXXX1000]": 42966, "[XXXXX622]": 42588, "[XXXXX708]": 42674, "[XXXXX85]": 42051, "[XXXXX987]": 42953, "[XXXXX500]": 42466, "[XXXXX996]": 42962, "[XXXXX850]": 42816, "[XXXXX849]": 42815, "[XXXXX307]": 42273, "[XXXXX130]": 42096, "[XXXXX169]": 42135, "[XXXXX38]": 42004, "[XXXXX152]": 42118, "[XXXXX993]": 42959, "[XXXXX652]": 42618, "[XXXXX239]": 42205, "[XXXXX306]": 42272, "[XXXXX111]": 42077, "[XXXXX204]": 42170, "[XXXXX769]": 42735, "[XXXXX123]": 42089, "[XXXXX625]": 42591, "[XXXXX183]": 42149, "[XXXXX900]": 42866, "[XXXXX200]": 42166, "[XXXXX937]": 42903, "[XXXXX896]": 42862, "[XXXXX389]": 42355, "[XXXXX296]": 42262, "[XXXXX928]": 42894, "[XXXXX274]": 42240, "[XXXXX716]": 42682, "[XXXXX83]": 42049, "[XXXXX35]": 42001, "[XXXXX314]": 42280, "[XXXXX144]": 42110, "[XXXXX833]": 42799, "[XXXXX188]": 42154, "[XXXXX470]": 42436, "[XXXXX393]": 42359, "[XXXXX555]": 42521, "[XXXXX41]": 42007, "[XXXXX701]": 42667, "[XXXXX162]": 42128, "[XXXXX966]": 42932, "[XXXXX824]": 42790, "[XXXXX741]": 42707, "[XXXXX412]": 42378, "[XXXXX978]": 42944, "[XXXXX781]": 42747, "[XXXXX392]": 42358, "[XXXXX338]": 42304, "[XXXXX62]": 42028, "[XXXXX895]": 42861, "[XXXXX924]": 42890, "[XXXXX1037]": 43003, "[XXXXX719]": 42685, "[XXXXX446]": 42412, "[XXXXX253]": 42219, "[XXXXX1016]": 42982, "[XXXXX13]": 41979, "[XXXXX271]": 42237, "[XXXXX455]": 42421, "[XXXXX384]": 42350, "[XXXXX436]": 42402, "[XXXXX712]": 42678, "[XXXXX919]": 42885, "[XXXXX976]": 42942, "[XXXXX558]": 42524, "[XXXXX217]": 42183, "[XXXXX266]": 42232, "[XXXXX779]": 42745, "[XXXXX385]": 42351, "[XXXXX332]": 42298, "[XXXXX373]": 42339, "[XXXXX561]": 42527, "[XXXXX151]": 42117, "[XXXXX196]": 42162, "[XXXXX429]": 42395, "[XXXXX846]": 42812, "[XXXXX0]": 41966, "[XXXXX237]": 42203, "[XXXXX440]": 42406, "[XXXXX471]": 42437, "[XXXXX336]": 42302, "[XXXXX32]": 41998, "[XXXXX679]": 42645, "[XXXXX720]": 42686, "[XXXXX419]": 42385, "[XXXXX402]": 42368, "[XXXXX685]": 42651, "[XXXXX104]": 42070, "[XXXXX731]": 42697, "[XXXXX947]": 42913, "[XXXXX934]": 42900, "[XXXXX394]": 42360, "[XXXXX288]": 42254, "[XXXXX742]": 42708, "[XXXXX665]": 42631, "[XXXXX734]": 42700, "[XXXXX8]": 41974, "[XXXXX549]": 42515, "[XXXXX461]": 42427, "[XXXXX25]": 41991, "[XXXXX475]": 42441, "[XXXXX231]": 42197, "[XXXXX586]": 42552, "[XXXXX871]": 42837, "[XXXXX898]": 42864, "[XXXXX485]": 42451, "[XXXXX148]": 42114, "[XXXXX115]": 42081, "[XXXXX503]": 42469, "[XXXXX199]": 42165, "[XXXXX814]": 42780, "[XXXXX775]": 42741, "[XXXXX1035]": 43001, "[XXXXX367]": 42333, "[XXXXX1013]": 42979, "[XXXXX968]": 42934, "[XXXXX510]": 42476, "[XXXXX573]": 42539, "[XXXXX222]": 42188, "[XXXXX450]": 42416, "[XXXXX634]": 42600, "[XXXXX174]": 42140, "[XXXXX379]": 42345, "[XXXXX816]": 42782, "[XXXXX113]": 42079, "[XXXXX317]": 42283, "[XXXXX664]": 42630, "[XXXXX180]": 42146, "[XXXXX540]": 42506, "[XXXXX857]": 42823, "[XXXXX528]": 42494, "[XXXXX945]": 42911, "[XXXXX656]": 42622, "[XXXXX396]": 42362, "[XXXXX571]": 42537, "[XXXXX680]": 42646, "[XXXXX439]": 42405, "[XXXXX89]": 42055, "[XXXXX364]": 42330, "[XXXXX163]": 42129, "[XXXXX92]": 42058, "[XXXXX189]": 42155, "[XXXXX102]": 42068, "[XXXXX733]": 42699, "[XXXXX280]": 42246, "[XXXXX76]": 42042, "[XXXXX72]": 42038, "[XXXXX21]": 41987, "[XXXXX99]": 42065, "[XXXXX717]": 42683, "[XXXXX961]": 42927, "[XXXXX11]": 41977, "[XXXXX516]": 42482, "[XXXXX120]": 42086, "[XXXXX1019]": 42985, "[XXXXX1034]": 43000, "[XXXXX397]": 42363, "[XXXXX1]": 41967, "[XXXXX34]": 42000, "[XXXXX738]": 42704, "[XXXXX295]": 42261, "[XXXXX260]": 42226, "[XXXXX972]": 42938, "[XXXXX452]": 42418, "[XXXXX230]": 42196, "[XXXXX337]": 42303, "[XXXXX421]": 42387, "[XXXXX538]": 42504, "[XXXXX353]": 42319, "[XXXXX704]": 42670, "[XXXXX911]": 42877, "[XXXXX641]": 42607, "[XXXXX609]": 42575, "[XXXXX290]": 42256, "[XXXXX691]": 42657, "[XXXXX305]": 42271, "[XXXXX416]": 42382, "[XXXXX1021]": 42987, "[XXXXX539]": 42505, "[XXXXX855]": 42821, "[XXXXX459]": 42425, "[XXXXX994]": 42960, "[XXXXX224]": 42190, "[XXXXX589]": 42555, "[XXXXX687]": 42653, "[XXXXX341]": 42307, "[XXXXX55]": 42021, "[XXXXX740]": 42706, "[XXXXX904]": 42870, "[XXXXX137]": 42103, "[XXXXX12]": 41978, "[XXXXX697]": 42663, "[XXXXX600]": 42566, "[XXXXX93]": 42059, "[XXXXX52]": 42018, "[XXXXX602]": 42568, "[XXXXX316]": 42282, "[XXXXX582]": 42548, "[XXXXX782]": 42748, "[XXXXX737]": 42703, "[XXXXX250]": 42216, "[XXXXX234]": 42200, "[XXXXX331]": 42297, "[XXXXX464]": 42430, "[XXXXX451]": 42417, "[XXXXX805]": 42771, "[XXXXX482]": 42448, "<pad>": 41964, "[XXXXX101]": 42067, "[XXXXX772]": 42738, "[XXXXX920]": 42886, "[XXXXX265]": 42231, "[XXXXX862]": 42828, "[XXXXX534]": 42500, "[XXXXX505]": 42471, "[XXXXX646]": 42612, "[XXXXX207]": 42173, "[XXXXX98]": 42064, "[XXXXX418]": 42384, "[XXXXX662]": 42628, "[XXXXX223]": 42189, "[XXXXX165]": 42131, "[XXXXX773]": 42739, "[XXXXX240]": 42206, "[XXXXX786]": 42752, "[XXXXX449]": 42415, "[XXXXX472]": 42438, "[XXXXX15]": 41981, "[XXXXX333]": 42299, "[XXXXX284]": 42250, "[XXXXX58]": 42024, "[XXXXX506]": 42472, "[XXXXX45]": 42011, "[XXXXX410]": 42376, "[XXXXX658]": 42624, "[XXXXX370]": 42336, "[XXXXX398]": 42364, "[XXXXX319]": 42285, "[XXXXX909]": 42875, "[XXXXX387]": 42353, "[XXXXX312]": 42278, "[XXXXX135]": 42101, "[XXXXX649]": 42615, "[XXXXX243]": 42209, "[XXXXX836]": 42802, "[XXXXX842]": 42808, "[XXXXX324]": 42290, "[XXXXX663]": 42629, "[XXXXX592]": 42558, "[XXXXX380]": 42346, "[XXXXX971]": 42937, "[XXXXX946]": 42912, "[XXXXX138]": 42104, "[XXXXX1004]": 42970, "[XXXXX960]": 42926, "[XXXXX864]": 42830, "[XXXXX628]": 42594, "[XXXXX794]": 42760, "[XXXXX969]": 42935, "[XXXXX277]": 42243, "[XXXXX100]": 42066, "[XXXXX724]": 42690, "[XXXXX173]": 42139, "[XXXXX156]": 42122, "[XXXXX812]": 42778, "[XXXXX841]": 42807, "[XXXXX29]": 41995, "[XXXXX682]": 42648, "[XXXXX335]": 42301, "[XXXXX82]": 42048, "[XXXXX374]": 42340, "[XXXXX601]": 42567, "[XXXXX594]": 42560, "[XXXXX468]": 42434, "[XXXXX289]": 42255, "[XXXXX238]": 42204, "[XXXXX831]": 42797, "[XXXXX967]": 42933, "[XXXXX212]": 42178, "[XXXXX718]": 42684, "[XXXXX31]": 41997, "[XXXXX851]": 42817, "[XXXXX129]": 42095, "[XXXXX191]": 42157, "[XXXXX348]": 42314, "[XXXXX795]": 42761, "[XXXXX40]": 42006, "[XXXXX525]": 42491, "[XXXXX1031]": 42997, "[XXXXX777]": 42743, "[XXXXX943]": 42909, "[XXXXX263]": 42229, "[XXXXX481]": 42447, "[XXXXX153]": 42119, "[XXXXX64]": 42030, "[XXXXX47]": 42013, "[XXXXX790]": 42756, "[XXXXX131]": 42097, "[XXXXX815]": 42781, "[XXXXX729]": 42695, "[XXXXX51]": 42017, "[XXXXX527]": 42493, "[XXXXX28]": 41994, "[XXXXX1028]": 42994, "[XXXXX603]": 42569, "[XXXXX334]": 42300, "[XXXXX843]": 42809, "[XXXXX989]": 42955, "[XXXXX941]": 42907, "[XXXXX604]": 42570, "[XXXXX214]": 42180, "[XXXXX762]": 42728, "[XXXXX608]": 42574, "[XXXXX519]": 42485, "[XXXXX141]": 42107, "[XXXXX802]": 42768, "[XXXXX884]": 42850, "[XXXXX847]": 42813, "[XXXXX415]": 42381, "[XXXXX356]": 42322, "[XXXXX378]": 42344, "[XXXXX673]": 42639, "[XXXXX283]": 42249, "[XXXXX56]": 42022, "[XXXXX822]": 42788, "[XXXXX695]": 42661, "[XXXXX445]": 42411, "[XXXXX770]": 42736, "[XXXXX523]": 42489, "[XXXXX640]": 42606, "[XXXXX366]": 42332, "[XXXXX300]": 42266, "[XXXXX557]": 42523, "[XXXXX512]": 42478, "[XXXXX182]": 42148, "[XXXXX172]": 42138, "[XXXXX22]": 41988, "[XXXXX876]": 42842, "[XXXXX7]": 41973, "[XXXXX1014]": 42980, "[XXXXX184]": 42150, "[XXXXX463]": 42429, "[XXXXX671]": 42637, "[XXXXX901]": 42867, "[XXXXX142]": 42108, "[XXXXX30]": 41996, "[XXXXX48]": 42014, "[XXXXX90]": 42056, "[XXXXX75]": 42041, "[XXXXX493]": 42459, "[XXXXX886]": 42852, "[XXXXX881]": 42847, "[XXXXX125]": 42091, "[XXXXX465]": 42431, "[XXXXX245]": 42211, "[XXXXX166]": 42132, "[XXXXX97]": 42063, "[XXXXX684]": 42650, "[XXXXX496]": 42462, "[XXXXX176]": 42142, "[XXXXX591]": 42557, "[XXXXX1003]": 42969, "[XXXXX479]": 42445, "[XXXXX526]": 42492, "[XXXXX830]": 42796, "[XXXXX428]": 42394, "[XXXXX2]": 41968, "[XXXXX94]": 42060, "[XXXXX636]": 42602, "[XXXXX550]": 42516, "[XXXXX959]": 42925, "[XXXXX150]": 42116, "[XXXXX286]": 42252, "[XXXXX688]": 42654, "[XXXXX618]": 42584, "[XXXXX899]": 42865, "[CLS]": 41962, "[XXXXX605]": 42571, "[XXXXX403]": 42369, "[XXXXX53]": 42019, "[XXXXX426]": 42392, "[XXXXX303]": 42269, "[XXXXX804]": 42770, "[XXXXX756]": 42722, "[XXXXX158]": 42124, "[XXXXX938]": 42904, "[XXXXX620]": 42586, "[XXXXX598]": 42564, "[XXXXX562]": 42528, "[XXXXX958]": 42924, "[XXXXX963]": 42929, "[XXXXX270]": 42236, "[XXXXX474]": 42440, "[XXXXX950]": 42916, "[XXXXX564]": 42530, "[XXXXX282]": 42248, "[XXXXX218]": 42184, "[XXXXX61]": 42027, "[XXXXX657]": 42623, "[XXXXX363]": 42329, "[XXXXX391]": 42357, "[XXXXX711]": 42677, "[XXXXX326]": 42292, "[XXXXX236]": 42202, "[XXXXX487]": 42453, "[XXXXX413]": 42379, "[XXXXX17]": 41983, "[XXXXX50]": 42016, "[XXXXX699]": 42665, "[XXXXX409]": 42375, "[XXXXX915]": 42881, "[XXXXX106]": 42072, "[XXXXX365]": 42331, "[XXXXX788]": 42754, "[XXXXX655]": 42621, "[XXXXX754]": 42720, "[XXXXX249]": 42215, "[XXXXX535]": 42501, "[XXXXX134]": 42100, "[XXXXX893]": 42859, "[XXXXX192]": 42158, "[XXXXX219]": 42185, "[XXXXX267]": 42233, "[XXXXX369]": 42335, "[XXXXX584]": 42550, "[XXXXX69]": 42035, "[XXXXX246]": 42212, "[XXXXX709]": 42675, "[XXXXX879]": 42845, "[XXXXX569]": 42535, "[XXXXX885]": 42851, "[XXXXX940]": 42906, "[XXXXX476]": 42442, "[XXXXX70]": 42036, "[XXXXX167]": 42133, "[XXXXX566]": 42532, "[XXXXX529]": 42495, "[XXXXX973]": 42939, "[XXXXX136]": 42102, "[XXXXX572]": 42538, "[XXXXX502]": 42468, "[XXXXX982]": 42948, "[XXXXX614]": 42580, "[XXXXX672]": 42638, "[XXXXX521]": 42487, "[XXXXX703]": 42669, "[XXXXX962]": 42928, "[XXXXX870]": 42836, "[XXXXX784]": 42750, "[XXXXX706]": 42672, "[XXXXX891]": 42857, "[XXXXX619]": 42585, "[XXXXX1038]": 43004, "[XXXXX577]": 42543, "[XXXXX309]": 42275, "[XXXXX208]": 42174, "[XXXXX735]": 42701, "[XXXXX87]": 42053, "[XXXXX522]": 42488, "[XXXXX621]": 42587, "[XXXXX511]": 42477, "[XXXXX546]": 42512, "[XXXXX26]": 41992, "[XXXXX803]": 42769, "[XXXXX327]": 42293, "[XXXXX4]": 41970, "[XXXXX799]": 42765, "[XXXXX653]": 42619, "[XXXXX965]": 42931, "[XXXXX128]": 42094, "[XXXXX213]": 42179, "[XXXXX574]": 42540, "[XXXXX1005]": 42971, "[XXXXX257]": 42223, "[XXXXX635]": 42601, "[XXXXX545]": 42511, "[XXXXX275]": 42241, "[XXXXX912]": 42878, "[XXXXX615]": 42581, "[XXXXX806]": 42772, "[XXXXX883]": 42849, "[XXXXX761]": 42727, "[XXXXX49]": 42015, "[XXXXX997]": 42963, "[XXXXX146]": 42112, "[XXXXX792]": 42758, "[XXXXX351]": 42317, "[XXXXX484]": 42450, "[XXXXX910]": 42876, "[XXXXX287]": 42253, "[XXXXX514]": 42480, "[XXXXX340]": 42306, "[XXXXX624]": 42590, "[XXXXX853]": 42819, "[XXXXX401]": 42367, "[XXXXX789]": 42755, "[XXXXX79]": 42045, "[XXXXX897]": 42863, "[XXXXX929]": 42895, "[XXXXX448]": 42414, "[XXXXX95]": 42061, "[XXXXX247]": 42213, "[XXXXX342]": 42308, "[XXXXX819]": 42785, "[XXXXX114]": 42080, "[XXXXX292]": 42258, "[XXXXX164]": 42130, "[XXXXX27]": 41993, "[XXXXX771]": 42737, "[XXXXX723]": 42689, "[XXXXX1002]": 42968, "[XXXXX355]": 42321, "[XXXXX755]": 42721, "[XXXXX596]": 42562, "[XXXXX630]": 42596, "[XXXXX651]": 42617, "[XXXXX986]": 42952, "[XXXXX256]": 42222, "[XXXXX330]": 42296, "[XXXXX438]": 42404, "[XXXXX60]": 42026, "[XXXXX1024]": 42990, "[XXXXX406]": 42372, "[XXXXX46]": 42012, "[XXXXX576]": 42542, "[XXXXX835]": 42801, "[XXXXX955]": 42921, "[XXXXX279]": 42245, "[XXXXX308]": 42274, "[XXXXX801]": 42767, "[XXXXX567]": 42533, "[XXXXX990]": 42956, "[XXXXX198]": 42164, "[XXXXX556]": 42522, "[XXXXX869]": 42835, "[XXXXX951]": 42917, "[XXXXX437]": 42403, "[XXXXX524]": 42490, "[XXXXX39]": 42005, "[XXXXX488]": 42454, "[XXXXX758]": 42724, "[XXXXX547]": 42513, "[XXXXX894]": 42860, "[XXXXX647]": 42613, "[XXXXX155]": 42121, "[XXXXX347]": 42313, "[XXXXX109]": 42075, "[XXXXX346]": 42312, "[XXXXX3]": 41969, "[XXXXX276]": 42242, "[XXXXX1029]": 42995, "[XXXXX1036]": 43002, "[XXXXX753]": 42719, "[XXXXX952]": 42918, "[XXXXX694]": 42660, "[XXXXX797]": 42763, "[XXXXX956]": 42922, "[XXXXX660]": 42626, "[XXXXX866]": 42832, "[XXXXX693]": 42659, "[XXXXX19]": 41985, "[XXXXX108]": 42074, "[XXXXX727]": 42693, "[XXXXX981]": 42947, "[XXXXX124]": 42090, "[XXXXX492]": 42458, "[XXXXX817]": 42783, "[XXXXX821]": 42787, "[XXXXX610]": 42576, "[XXXXX122]": 42088, "[XXXXX118]": 42084, "[XXXXX344]": 42310, "[XXXXX828]": 42794, "[XXXXX193]": 42159, "[XXXXX721]": 42687, "[XXXXX834]": 42800, "[XXXXX195]": 42161, "[XXXXX110]": 42076, "[XXXXX1022]": 42988, "[XXXXX107]": 42073, "[XXXXX542]": 42508, "[XXXXX808]": 42774, "[XXXXX889]": 42855, "[XXXXX430]": 42396, "[XXXXX121]": 42087, "[XXXXX700]": 42666, "[XXXXX66]": 42032, "[XXXXX765]": 42731, "[XXXXX728]": 42694, "[XXXXX954]": 42920, "[XXXXX626]": 42592, "[XXXXX454]": 42420, "[XXXXX147]": 42113, "[XXXXX33]": 41999, "[XXXXX633]": 42599, "[XXXXX588]": 42554, "[XXXXX381]": 42347, "[XXXXX796]": 42762, "[XXXXX407]": 42373, "[XXXXX480]": 42446, "[XXXXX764]": 42730, "[XXXXX206]": 42172, "[XXXXX953]": 42919, "[XXXXX757]": 42723, "[XXXXX68]": 42034, "[XXXXX553]": 42519, "[XXXXX743]": 42709, "[XXXXX232]": 42198, "[XXXXX127]": 42093, "[XXXXX425]": 42391, "[XXXXX580]": 42546, "[XXXXX442]": 42408, "[XXXXX575]": 42541, "[XXXXX696]": 42662, "[XXXXX935]": 42901, "[XXXXX382]": 42348, "[XXXXX593]": 42559, "[XXXXX499]": 42465, "[XXXXX863]": 42829, "[XXXXX399]": 42365, "[XXXXX221]": 42187, "[XXXXX422]": 42388, "[XXXXX579]": 42545, "[XXXXX710]": 42676, "[XXXXX1041]": 43007, "[XXXXX985]": 42951, "[XXXXX844]": 42810, "[XXXXX6]": 41972, "[XXXXX220]": 42186, "[XXXXX328]": 42294, "[XXXXX273]": 42239, "[XXXXX933]": 42899, "[XXXXX242]": 42208, "[XXXXX1032]": 42998, "[XXXXX209]": 42175, "[XXXXX171]": 42137, "[XXXXX916]": 42882, "[XXXXX467]": 42433, "[XXXXX447]": 42413, "[XXXXX998]": 42964, "[XXXXX918]": 42884, "[XXXXX914]": 42880, "[XXXXX730]": 42696, "[XXXXX859]": 42825, "[XXXXX686]": 42652, "[XXXXX24]": 41990, "[XXXXX187]": 42153, "[XXXXX248]": 42214, "[XXXXX810]": 42776, "[XXXXX681]": 42647, "[XXXXX746]": 42712, "[XXXXX541]": 42507, "[XXXXX400]": 42366, "[XXXXX201]": 42167, "[XXXXX689]": 42655, "[XXXXX988]": 42954, "[XXXXX160]": 42126, "[XXXXX825]": 42791, "[XXXXX352]": 42318, "[XXXXX616]": 42582, "[XXXXX299]": 42265, "[XXXXX1015]": 42981, "[XXXXX388]": 42354, "[XXXXX763]": 42729, "[XXXXX408]": 42374, "[XXXXX548]": 42514, "[XXXXX302]": 42268, "[XXXXX570]": 42536, "[XXXXX84]": 42050, "[XXXXX178]": 42144, "[XXXXX74]": 42040, "[XXXXX23]": 41989, "[XXXXX54]": 42020, "[XXXXX829]": 42795, "[XXXXX714]": 42680, "[XXXXX71]": 42037, "[XXXXX458]": 42424, "[XXXXX983]": 42949, "[XXXXX132]": 42098, "[XXXXX460]": 42426, "[XXXXX411]": 42377, "[XXXXX170]": 42136, "[XXXXX417]": 42383, "[XXXXX654]": 42620, "[XXXXX631]": 42597, "[XXXXX873]": 42839, "[XXXXX543]": 42509, "[XXXXX310]": 42276, "[XXXXX339]": 42305, "[XXXXX228]": 42194, "[XXXXX827]": 42793, "[XXXXX617]": 42583, "[XXXXX43]": 42009, "[XXXXX926]": 42892, "[XXXXX37]": 42003, "[XXXXX977]": 42943, "[XXXXX980]": 42946, "[XXXXX925]": 42891, "[XXXXX140]": 42106, "[XXXXX103]": 42069, "[XXXXX1025]": 42991, "[XXXXX360]": 42326, "[XXXXX515]": 42481, "[XXXXX202]": 42168, "[XXXXX278]": 42244, "[XXXXX975]": 42941, "[XXXXX143]": 42109, "[XXXXX722]": 42688, "[XXXXX258]": 42224, "[XXXXX536]": 42502, "[XXXXX532]": 42498, "[XXXXX291]": 42257, "[XXXXX1027]": 42993, "[XXXXX86]": 42052, "[XXXXX643]": 42609, "[XXXXX944]": 42910, "[XXXXX65]": 42031, "[XXXXX890]": 42856, "[XXXXX565]": 42531, "[XXXXX311]": 42277, "[XXXXX583]": 42549, "[XXXXX349]": 42315, "[XXXXX752]": 42718, "[XXXXX432]": 42398, "[XXXXX298]": 42264, "[XXXXX5]": 41971, "[XXXXX903]": 42869, "[XXXXX383]": 42349, "[XXXXX725]": 42691, "[XXXXX434]": 42400, "[XXXXX116]": 42082, "[XXXXX599]": 42565, "[XXXXX902]": 42868, "[XXXXX36]": 42002, "[XXXXX469]": 42435, "[XXXXX329]": 42295, "[XXXXX907]": 42873, "[XXXXX491]": 42457, "[XXXXX927]": 42893, "[XXXXX595]": 42561, "[XXXXX139]": 42105, "[XXXXX252]": 42218, "[XXXXX462]": 42428, "[XXXXX751]": 42717, "[XXXXX361]": 42327, "[XXXXX318]": 42284, "[XXXXX551]": 42517, "[XXXXX826]": 42792, "[XXXXX559]": 42525, "[XXXXX670]": 42636, "[XXXXX313]": 42279, "[XXXXX874]": 42840, "[XXXXX749]": 42715, "[XXXXX780]": 42746, "[XXXXX504]": 42470, "[XXXXX63]": 42029, "[XXXXX838]": 42804, "[XXXXX320]": 42286, "[XXXXX145]": 42111, "[XXXXX14]": 41980, "[XXXXX386]": 42352, "[XXXXX181]": 42147, "[XXXXX949]": 42915, "[XXXXX414]": 42380, "[XXXXX16]": 41982, "[XXXXX254]": 42220, "[XXXXX818]": 42784, "[XXXXX229]": 42195, "[XXXXX424]": 42390, "[XXXXX371]": 42337, "[XXXXX563]": 42529, "[XXXXX791]": 42757, "[XXXXX852]": 42818, "[XXXXX768]": 42734, "[XXXXX42]": 42008, "[XXXXX501]": 42467, "[XXXXX698]": 42664, "[XXXXX999]": 42965, "[XXXXX251]": 42217, "[XXXXX845]": 42811, "[XXXXX860]": 42826, "[XXXXX887]": 42853, "[XXXXX427]": 42393, "[XXXXX661]": 42627, "[XXXXX942]": 42908, "[XXXXX880]": 42846, "[XXXXX518]": 42484, "[XXXXX669]": 42635, "[XXXXX473]": 42439, "[XXXXX992]": 42958, "[XXXXX126]": 42092, "[XXXXX713]": 42679, "[XXXXX377]": 42343, "[XXXXX322]": 42288, "[XXXXX443]": 42409, "[XXXXX91]": 42057, "[XXXXX477]": 42443, "[XXXXX537]": 42503, "[XXXXX759]": 42725, "[XXXXX255]": 42221, "[XXXXX297]": 42263, "[XXXXX793]": 42759, "[XXXXX627]": 42593, "[XXXXX268]": 42234, "[XXXXX650]": 42616, "[XXXXX235]": 42201, "[XXXXX478]": 42444, "[XXXXX923]": 42889, "[XXXXX293]": 42259, "[XXXXX668]": 42634, "[XXXXX1011]": 42977, "[XXXXX194]": 42160, "[XXXXX457]": 42423, "[XXXXX486]": 42452, "[XXXXX433]": 42399, "[XXXXX1008]": 42974, "[XXXXX861]": 42827, "[XXXXX1030]": 42996, "[XXXXX979]": 42945, "[XXXXX888]": 42854, "[XXXXX623]": 42589, "[XXXXX856]": 42822}
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]"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c73202453c2356efa2c101e27de9cdbe35a3685191f3f505344b433b1d5d7a
3
+ size 955538
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/lub_latn_5mb", "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "models/5mb/lub_latn_5mb/special_tokens_map.json", "tokenizer_class": "AlbertTokenizer"}