goldfish-models commited on
Commit
da0f6e9
·
1 Parent(s): d7d1860

Upload srn_latn_5mb tokenizer.

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[XXXXX311]": 16175, "[XXXXX197]": 16061, "[XXXXX188]": 16052, "[XXXXX208]": 16072, "[XXXXX30]": 15894, "[XXXXX172]": 16036, "[XXXXX107]": 15971, "[XXXXX211]": 16075, "[XXXXX93]": 15957, "[XXXXX470]": 16334, "[XXXXX44]": 15908, "[XXXXX416]": 16280, "[XXXXX424]": 16288, "[XXXXX250]": 16114, "[XXXXX192]": 16056, "[XXXXX340]": 16204, "[XXXXX147]": 16011, "[XXXXX179]": 16043, "[XXXXX438]": 16302, "[XXXXX67]": 15931, "[XXXXX14]": 15878, "[XXXXX10]": 15874, "[XXXXX176]": 16040, "[XXXXX253]": 16117, "[XXXXX345]": 16209, "[XXXXX358]": 16222, "[XXXXX225]": 16089, "[XXXXX66]": 15930, "[XXXXX271]": 16135, "[XXXXX350]": 16214, "[XXXXX432]": 16296, "[XXXXX29]": 15893, "[XXXXX194]": 16058, "[XXXXX471]": 16335, "[XXXXX412]": 16276, "[XXXXX166]": 16030, "[XXXXX55]": 15919, "[XXXXX90]": 15954, "[XXXXX404]": 16268, "[XXXXX62]": 15926, "[XXXXX152]": 16016, "[XXXXX466]": 16330, "[XXXXX111]": 15975, "[XXXXX231]": 16095, "[XXXXX280]": 16144, "[XXXXX187]": 16051, "[XXXXX217]": 16081, "[XXXXX304]": 16168, "[XXXXX456]": 16320, "[XXXXX48]": 15912, "[XXXXX227]": 16091, "[XXXXX293]": 16157, "[XXXXX128]": 15992, "[XXXXX185]": 16049, "[XXXXX6]": 15870, "[XXXXX320]": 16184, "[XXXXX235]": 16099, "[XXXXX331]": 16195, "[XXXXX15]": 15879, "[XXXXX367]": 16231, "[XXXXX460]": 16324, "[XXXXX265]": 16129, "[XXXXX429]": 16293, "[XXXXX125]": 15989, "[XXXXX510]": 16374, "[XXXXX112]": 15976, "[XXXXX122]": 15986, "[XXXXX191]": 16055, "[XXXXX224]": 16088, "[XXXXX2]": 15866, "[XXXXX148]": 16012, "[XXXXX338]": 16202, "[XXXXX254]": 16118, "[XXXXX175]": 16039, "[XXXXX281]": 16145, "[XXXXX133]": 15997, "[XXXXX36]": 15900, "[XXXXX405]": 16269, "[XXXXX384]": 16248, "[XXXXX16]": 15880, "[XXXXX389]": 16253, "[XXXXX496]": 16360, "[XXXXX226]": 16090, "[XXXXX39]": 15903, "[XXXXX336]": 16200, "[XXXXX495]": 16359, "[XXXXX163]": 16027, "[XXXXX507]": 16371, "[XXXXX353]": 16217, "[XXXXX430]": 16294, "[XXXXX342]": 16206, "[XXXXX123]": 15987, "[XXXXX214]": 16078, "[XXXXX303]": 16167, "[XXXXX317]": 16181, "[XXXXX79]": 15943, "[XXXXX157]": 16021, "[XXXXX205]": 16069, "[XXXXX446]": 16310, "[XXXXX215]": 16079, "[XXXXX360]": 16224, "[XXXXX246]": 16110, "[XXXXX24]": 15888, "[XXXXX220]": 16084, "[XXXXX489]": 16353, "[XXXXX193]": 16057, "[XXXXX316]": 16180, "[XXXXX73]": 15937, "[XXXXX487]": 16351, "[XXXXX454]": 16318, "[XXXXX346]": 16210, "[XXXXX174]": 16038, "[XXXXX59]": 15923, "[XXXXX13]": 15877, "[XXXXX146]": 16010, "[XXXXX422]": 16286, "[XXXXX262]": 16126, "[XXXXX373]": 16237, "[MASK]": 15863, "[XXXXX110]": 15974, "[XXXXX431]": 16295, "[XXXXX448]": 16312, "[XXXXX369]": 16233, "[XXXXX230]": 16094, "[XXXXX283]": 16147, "[XXXXX457]": 16321, "[XXXXX31]": 15895, "[XXXXX182]": 16046, "[XXXXX390]": 16254, "[XXXXX239]": 16103, "[XXXXX183]": 16047, "[XXXXX356]": 16220, "[XXXXX494]": 16358, "[XXXXX282]": 16146, "[XXXXX116]": 15980, "[XXXXX61]": 15925, "[XXXXX395]": 16259, "[XXXXX173]": 16037, "[XXXXX444]": 16308, "[XXXXX54]": 15918, "[XXXXX238]": 16102, "[XXXXX20]": 15884, "[XXXXX143]": 16007, "[XXXXX155]": 16019, "<pad>": 15862, "[XXXXX222]": 16086, "[XXXXX478]": 16342, "[XXXXX76]": 15940, "[XXXXX420]": 16284, "[XXXXX160]": 16024, "[XXXXX497]": 16361, "[XXXXX381]": 16245, "[XXXXX365]": 16229, "[XXXXX302]": 16166, "[XXXXX51]": 15915, "[XXXXX485]": 16349, "[XXXXX366]": 16230, "[XXXXX141]": 16005, "[XXXXX502]": 16366, "[XXXXX387]": 16251, "[XXXXX57]": 15921, "[XXXXX402]": 16266, "[XXXXX11]": 15875, "[XXXXX274]": 16138, "[XXXXX436]": 16300, "[XXXXX334]": 16198, "[XXXXX268]": 16132, "[XXXXX285]": 16149, "[XXXXX321]": 16185, "[XXXXX203]": 16067, "[XXXXX255]": 16119, "[XXXXX458]": 16322, "[XXXXX145]": 16009, "[XXXXX118]": 15982, "[XXXXX137]": 16001, "[XXXXX102]": 15966, "[XXXXX232]": 16096, "[XXXXX63]": 15927, "[XXXXX287]": 16151, "[XXXXX196]": 16060, "[XXXXX64]": 15928, "[XXXXX319]": 16183, "[XXXXX292]": 16156, "[XXXXX218]": 16082, "[XXXXX354]": 16218, "[XXXXX406]": 16270, "[XXXXX12]": 15876, "[XXXXX313]": 16177, "[XXXXX335]": 16199, "[XXXXX86]": 15950, "[XXXXX300]": 16164, "[XXXXX131]": 15995, "[XXXXX493]": 16357, "[XXXXX168]": 16032, "[XXXXX132]": 15996, "[XXXXX452]": 16316, "[XXXXX68]": 15932, "[XXXXX87]": 15951, "[XXXXX505]": 16369, "[XXXXX75]": 15939, "[XXXXX85]": 15949, "[XXXXX348]": 16212, "[XXXXX443]": 16307, "[XXXXX103]": 15967, "[XXXXX88]": 15952, "[XXXXX33]": 15897, "[XXXXX343]": 16207, "[XXXXX158]": 16022, "[XXXXX407]": 16271, "[XXXXX413]": 16277, "[XXXXX1]": 15865, "[XXXXX371]": 16235, "[XXXXX82]": 15946, "[XXXXX108]": 15972, "[XXXXX427]": 16291, "[XXXXX392]": 16256, "[XXXXX472]": 16336, "[XXXXX266]": 16130, "[XXXXX117]": 15981, "[XXXXX58]": 15922, "[XXXXX308]": 16172, "[XXXXX511]": 16375, "[XXXXX249]": 16113, "[XXXXX323]": 16187, "[XXXXX453]": 16317, "[XXXXX56]": 15920, "[XXXXX159]": 16023, "[XXXXX325]": 16189, "[XXXXX201]": 16065, "[XXXXX322]": 16186, "[XXXXX142]": 16006, "[XXXXX178]": 16042, "[XXXXX101]": 15965, "[XXXXX450]": 16314, "[XXXXX199]": 16063, "[XXXXX503]": 16367, "[XXXXX264]": 16128, "[XXXXX377]": 16241, "[XXXXX445]": 16309, "[XXXXX5]": 15869, "[XXXXX237]": 16101, "[XXXXX3]": 15867, "[XXXXX399]": 16263, "[XXXXX153]": 16017, "[XXXXX362]": 16226, "[XXXXX40]": 15904, "[XXXXX269]": 16133, "[XXXXX46]": 15910, "[XXXXX138]": 16002, "[XXXXX372]": 16236, "[XXXXX326]": 16190, "[XXXXX339]": 16203, "[XXXXX252]": 16116, "[XXXXX91]": 15955, "[XXXXX455]": 16319, "[XXXXX517]": 16381, "[XXXXX393]": 16257, "[XXXXX34]": 15898, "[XXXXX77]": 15941, "[XXXXX386]": 16250, "[XXXXX184]": 16048, "[XXXXX347]": 16211, "[XXXXX92]": 15956, "[XXXXX441]": 16305, "[XXXXX95]": 15959, "[XXXXX421]": 16285, "[XXXXX190]": 16054, "[XXXXX261]": 16125, "[XXXXX200]": 16064, "[XXXXX461]": 16325, "[XXXXX275]": 16139, "[XXXXX284]": 16148, "[XXXXX242]": 16106, "[XXXXX263]": 16127, "[XXXXX139]": 16003, "[XXXXX417]": 16281, "[XXXXX305]": 16169, "[XXXXX435]": 16299, "[XXXXX500]": 16364, "[XXXXX120]": 15984, "[XXXXX514]": 16378, "[XXXXX213]": 16077, "[XXXXX341]": 16205, "[XXXXX150]": 16014, "[XXXXX370]": 16234, "[XXXXX481]": 16345, "[XXXXX229]": 16093, "[XXXXX245]": 16109, "[XXXXX4]": 15868, "[XXXXX279]": 16143, "[XXXXX42]": 15906, "[XXXXX423]": 16287, "[XXXXX99]": 15963, "[XXXXX65]": 15929, "[XXXXX329]": 16193, "[XXXXX298]": 16162, "[XXXXX162]": 16026, "[XXXXX43]": 15907, "[XXXXX212]": 16076, "[XXXXX144]": 16008, "[XXXXX98]": 15962, "[XXXXX105]": 15969, "[XXXXX504]": 16368, "[XXXXX410]": 16274, "[XXXXX368]": 16232, "[XXXXX301]": 16165, "[XXXXX136]": 16000, "[XXXXX400]": 16264, "[XXXXX506]": 16370, "[XXXXX401]": 16265, "[XXXXX23]": 15887, "[XXXXX440]": 16304, "[XXXXX418]": 16282, "[XXXXX425]": 16289, "[XXXXX22]": 15886, "[XXXXX290]": 16154, "[XXXXX414]": 16278, "[XXXXX171]": 16035, "[XXXXX349]": 16213, "[XXXXX94]": 15958, "[XXXXX291]": 16155, "[XXXXX408]": 16272, "[XXXXX434]": 16298, "[XXXXX154]": 16018, "[XXXXX121]": 15985, "[XXXXX209]": 16073, "[XXXXX509]": 16373, "[XXXXX151]": 16015, "[XXXXX32]": 15896, "[XXXXX257]": 16121, "[XXXXX463]": 16327, "[XXXXX380]": 16244, "[XXXXX465]": 16329, "[XXXXX310]": 16174, "[XXXXX17]": 15881, "[XXXXX206]": 16070, "[XXXXX8]": 15872, "[XXXXX415]": 16279, "[XXXXX0]": 15864, "[XXXXX307]": 16171, "[XXXXX72]": 15936, "[XXXXX241]": 16105, "[XXXXX96]": 15960, "[XXXXX388]": 16252, "[XXXXX19]": 15883, "[XXXXX115]": 15979, "[SEP]": 15861, "[XXXXX97]": 15961, "[XXXXX473]": 16337, "[XXXXX233]": 16097, "[XXXXX288]": 16152, "[XXXXX437]": 16301, "[XXXXX119]": 15983, "[XXXXX267]": 16131, "[XXXXX299]": 16163, "[XXXXX490]": 16354, "[XXXXX361]": 16225, "[XXXXX165]": 16029, "[XXXXX518]": 16382, "[XXXXX27]": 15891, "[XXXXX130]": 15994, "[XXXXX35]": 15899, "[XXXXX516]": 16380, "[XXXXX327]": 16191, "[XXXXX330]": 16194, "[XXXXX519]": 16383, "[XXXXX484]": 16348, "[XXXXX351]": 16215, "[XXXXX286]": 16150, "[XXXXX312]": 16176, "[XXXXX202]": 16066, "[XXXXX9]": 15873, "[XXXXX219]": 16083, "[XXXXX70]": 15934, "[XXXXX428]": 16292, "[XXXXX309]": 16173, "[XXXXX324]": 16188, "[XXXXX81]": 15945, "[XXXXX161]": 16025, "[XXXXX247]": 16111, "[XXXXX486]": 16350, "[XXXXX80]": 15944, "[XXXXX134]": 15998, "[XXXXX195]": 16059, "[XXXXX149]": 16013, "[XXXXX21]": 15885, "[XXXXX344]": 16208, "[XXXXX469]": 16333, "[XXXXX439]": 16303, "[XXXXX113]": 15977, "[XXXXX100]": 15964, "[XXXXX474]": 16338, "[XXXXX156]": 16020, "[XXXXX260]": 16124, "[XXXXX364]": 16228, "[XXXXX459]": 16323, "[XXXXX71]": 15935, "[XXXXX69]": 15933, "[XXXXX411]": 16275, "[XXXXX169]": 16033, "[XXXXX50]": 15914, "[XXXXX106]": 15970, "[XXXXX382]": 16246, "[XXXXX240]": 16104, "[XXXXX53]": 15917, "[XXXXX26]": 15890, "[XXXXX419]": 16283, "[XXXXX374]": 16238, "[XXXXX210]": 16074, "[XXXXX25]": 15889, "[XXXXX483]": 16347, "[XXXXX433]": 16297, "[XXXXX28]": 15892, "[XXXXX170]": 16034, "[XXXXX47]": 15911, "[XXXXX7]": 15871, "[XXXXX492]": 16356, "[XXXXX78]": 15942, "[XXXXX359]": 16223, "[XXXXX243]": 16107, "[XXXXX258]": 16122, "[XXXXX207]": 16071, "[XXXXX333]": 16197, "[XXXXX508]": 16372, "[XXXXX409]": 16273, "[XXXXX394]": 16258, "[XXXXX296]": 16160, "[XXXXX74]": 15938, "[XXXXX314]": 16178, "[XXXXX501]": 16365, "[XXXXX124]": 15988, "[XXXXX248]": 16112, "[XXXXX403]": 16267, "[XXXXX464]": 16328, "[XXXXX135]": 15999, "[XXXXX391]": 16255, "[XXXXX397]": 16261, "[XXXXX189]": 16053, "[XXXXX104]": 15968, "[XXXXX512]": 16376, "[XXXXX186]": 16050, "[XXXXX376]": 16240, "[XXXXX447]": 16311, "[XXXXX383]": 16247, "[XXXXX294]": 16158, "[XXXXX328]": 16192, "[XXXXX273]": 16137, "[XXXXX277]": 16141, "[XXXXX482]": 16346, "[XXXXX126]": 15990, "[XXXXX462]": 16326, "[XXXXX375]": 16239, "[XXXXX236]": 16100, "[XXXXX270]": 16134, "[XXXXX476]": 16340, "[XXXXX297]": 16161, "[XXXXX477]": 16341, "[XXXXX140]": 16004, "[XXXXX385]": 16249, "[XXXXX198]": 16062, "[XXXXX89]": 15953, "[XXXXX498]": 16362, "[XXXXX315]": 16179, "[XXXXX396]": 16260, "[XXXXX37]": 15901, "[XXXXX244]": 16108, "[XXXXX228]": 16092, "[XXXXX442]": 16306, "[XXXXX84]": 15948, "[XXXXX398]": 16262, "[XXXXX352]": 16216, "[XXXXX127]": 15991, "[XXXXX221]": 16085, "[XXXXX164]": 16028, "[XXXXX515]": 16379, "[XXXXX204]": 16068, "[XXXXX181]": 16045, "[XXXXX41]": 15905, "[XXXXX488]": 16352, "[XXXXX332]": 16196, "[XXXXX18]": 15882, "[XXXXX60]": 15924, "[CLS]": 15860, "[XXXXX491]": 16355, "[XXXXX234]": 16098, "[XXXXX276]": 16140, "[XXXXX467]": 16331, "[XXXXX177]": 16041, "[XXXXX363]": 16227, "[XXXXX295]": 16159, "[XXXXX289]": 16153, "[XXXXX479]": 16343, "[XXXXX167]": 16031, "[XXXXX114]": 15978, "[XXXXX45]": 15909, "[XXXXX223]": 16087, "[XXXXX426]": 16290, "[XXXXX357]": 16221, "[XXXXX451]": 16315, "[XXXXX379]": 16243, "[XXXXX216]": 16080, "[XXXXX306]": 16170, "[XXXXX499]": 16363, "[XXXXX513]": 16377, "[XXXXX355]": 16219, "[XXXXX38]": 15902, "[XXXXX251]": 16115, "[XXXXX480]": 16344, "[XXXXX259]": 16123, "[XXXXX52]": 15916, "[XXXXX278]": 16142, "[XXXXX180]": 16044, "[XXXXX129]": 15993, "[XXXXX109]": 15973, "[XXXXX318]": 16182, "[XXXXX272]": 16136, "[XXXXX49]": 15913, "[XXXXX337]": 16201, "[XXXXX83]": 15947, "[XXXXX449]": 16313, "[XXXXX256]": 16120, "[XXXXX468]": 16332, "[XXXXX378]": 16242, "[XXXXX475]": 16339}
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]"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7467937fd64df9d00996ec8a25dd08c3bf582c0201465e99e2685840ff3b54f
3
+ size 484521
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/srn_latn_5mb", "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "models/5mb/srn_latn_5mb/special_tokens_map.json", "tokenizer_class": "AlbertTokenizer"}