Commit ·
fda9a35
1
Parent(s): 014fc80
Upload tokenizer
Browse files- added_tokens.json +445 -0
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +2 -2
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"CASE_-ve": 65119,
|
| 3 |
+
"CASE_Chium": 65187,
|
| 4 |
+
"CASE_Domini": 65225,
|
| 5 |
+
"CASE_Erant": 65208,
|
| 6 |
+
"CASE_Erat": 65394,
|
| 7 |
+
"CASE_Erit": 65019,
|
| 8 |
+
"CASE_Erunt": 65189,
|
| 9 |
+
"CASE_Gallis": 65375,
|
| 10 |
+
"CASE_a": 65145,
|
| 11 |
+
"CASE_abam": 65353,
|
| 12 |
+
"CASE_abamini": 65047,
|
| 13 |
+
"CASE_abamur": 65091,
|
| 14 |
+
"CASE_abamus": 65197,
|
| 15 |
+
"CASE_abant": 65376,
|
| 16 |
+
"CASE_abantur": 65365,
|
| 17 |
+
"CASE_abar": 65087,
|
| 18 |
+
"CASE_abare": 65028,
|
| 19 |
+
"CASE_abaris": 65254,
|
| 20 |
+
"CASE_abas": 65215,
|
| 21 |
+
"CASE_abat": 65210,
|
| 22 |
+
"CASE_abatis": 65148,
|
| 23 |
+
"CASE_abatur": 65190,
|
| 24 |
+
"CASE_abere": 65329,
|
| 25 |
+
"CASE_aberis": 65355,
|
| 26 |
+
"CASE_abimini": 65135,
|
| 27 |
+
"CASE_abimur": 65272,
|
| 28 |
+
"CASE_abimus": 65193,
|
| 29 |
+
"CASE_abis": 65037,
|
| 30 |
+
"CASE_abit": 65084,
|
| 31 |
+
"CASE_abitis": 65359,
|
| 32 |
+
"CASE_abitur": 65199,
|
| 33 |
+
"CASE_abo": 65413,
|
| 34 |
+
"CASE_abor": 65083,
|
| 35 |
+
"CASE_abunt": 65222,
|
| 36 |
+
"CASE_abuntur": 65082,
|
| 37 |
+
"CASE_abus": 65290,
|
| 38 |
+
"CASE_ac": 65104,
|
| 39 |
+
"CASE_accersendus": 65001,
|
| 40 |
+
"CASE_ad": 65318,
|
| 41 |
+
"CASE_ae": 65267,
|
| 42 |
+
"CASE_aec": 65410,
|
| 43 |
+
"CASE_ai": 65195,
|
| 44 |
+
"CASE_am": 65102,
|
| 45 |
+
"CASE_amini": 65122,
|
| 46 |
+
"CASE_amore": 65044,
|
| 47 |
+
"CASE_amur": 65137,
|
| 48 |
+
"CASE_amus": 65229,
|
| 49 |
+
"CASE_an": 65095,
|
| 50 |
+
"CASE_anc": 65060,
|
| 51 |
+
"CASE_anda": 65311,
|
| 52 |
+
"CASE_andae": 65053,
|
| 53 |
+
"CASE_andam": 65024,
|
| 54 |
+
"CASE_andarum": 65227,
|
| 55 |
+
"CASE_andas": 65027,
|
| 56 |
+
"CASE_ande": 65156,
|
| 57 |
+
"CASE_andi": 65319,
|
| 58 |
+
"CASE_andis": 65282,
|
| 59 |
+
"CASE_ando": 65221,
|
| 60 |
+
"CASE_andorum": 65045,
|
| 61 |
+
"CASE_andos": 65274,
|
| 62 |
+
"CASE_andum": 65256,
|
| 63 |
+
"CASE_andus": 65160,
|
| 64 |
+
"CASE_ans": 65219,
|
| 65 |
+
"CASE_ant": 65432,
|
| 66 |
+
"CASE_ante": 65246,
|
| 67 |
+
"CASE_antem": 65379,
|
| 68 |
+
"CASE_antes": 65025,
|
| 69 |
+
"CASE_anti": 65356,
|
| 70 |
+
"CASE_antia": 65100,
|
| 71 |
+
"CASE_antibus": 65377,
|
| 72 |
+
"CASE_antis": 65308,
|
| 73 |
+
"CASE_antium": 65239,
|
| 74 |
+
"CASE_anto": 65245,
|
| 75 |
+
"CASE_antum": 65074,
|
| 76 |
+
"CASE_antur": 65056,
|
| 77 |
+
"CASE_ar": 65317,
|
| 78 |
+
"CASE_arce": 65166,
|
| 79 |
+
"CASE_are": 65350,
|
| 80 |
+
"CASE_arem": 65436,
|
| 81 |
+
"CASE_aremini": 65134,
|
| 82 |
+
"CASE_aremur": 65280,
|
| 83 |
+
"CASE_aremus": 65105,
|
| 84 |
+
"CASE_arent": 65258,
|
| 85 |
+
"CASE_arentur": 65275,
|
| 86 |
+
"CASE_arer": 65341,
|
| 87 |
+
"CASE_arere": 65427,
|
| 88 |
+
"CASE_areris": 65315,
|
| 89 |
+
"CASE_ares": 65198,
|
| 90 |
+
"CASE_aret": 65062,
|
| 91 |
+
"CASE_aretis": 65063,
|
| 92 |
+
"CASE_aretur": 65079,
|
| 93 |
+
"CASE_ari": 65211,
|
| 94 |
+
"CASE_arier": 65276,
|
| 95 |
+
"CASE_aris": 65098,
|
| 96 |
+
"CASE_armis": 65362,
|
| 97 |
+
"CASE_arum": 65106,
|
| 98 |
+
"CASE_arun": 65069,
|
| 99 |
+
"CASE_as": 65327,
|
| 100 |
+
"CASE_at": 65278,
|
| 101 |
+
"CASE_ate": 65302,
|
| 102 |
+
"CASE_atis": 65011,
|
| 103 |
+
"CASE_ato": 65396,
|
| 104 |
+
"CASE_ator": 65223,
|
| 105 |
+
"CASE_atote": 65109,
|
| 106 |
+
"CASE_atur": 65200,
|
| 107 |
+
"CASE_autem": 65174,
|
| 108 |
+
"CASE_bam": 65124,
|
| 109 |
+
"CASE_bamus": 65249,
|
| 110 |
+
"CASE_bant": 65155,
|
| 111 |
+
"CASE_bantur": 65403,
|
| 112 |
+
"CASE_bas": 65188,
|
| 113 |
+
"CASE_bat": 65435,
|
| 114 |
+
"CASE_batur": 65112,
|
| 115 |
+
"CASE_bimus": 65228,
|
| 116 |
+
"CASE_bis": 65206,
|
| 117 |
+
"CASE_bit": 65192,
|
| 118 |
+
"CASE_bitis": 65434,
|
| 119 |
+
"CASE_bo": 65264,
|
| 120 |
+
"CASE_bunt": 65441,
|
| 121 |
+
"CASE_circuitu": 65247,
|
| 122 |
+
"CASE_d": 65054,
|
| 123 |
+
"CASE_diebus": 65387,
|
| 124 |
+
"CASE_dolo": 65131,
|
| 125 |
+
"CASE_e": 65404,
|
| 126 |
+
"CASE_eam": 65234,
|
| 127 |
+
"CASE_eamini": 65214,
|
| 128 |
+
"CASE_eamur": 65399,
|
| 129 |
+
"CASE_eamus": 65186,
|
| 130 |
+
"CASE_eant": 65077,
|
| 131 |
+
"CASE_eantur": 65354,
|
| 132 |
+
"CASE_ear": 65163,
|
| 133 |
+
"CASE_eare": 65041,
|
| 134 |
+
"CASE_earis": 65370,
|
| 135 |
+
"CASE_eas": 65409,
|
| 136 |
+
"CASE_eat": 65291,
|
| 137 |
+
"CASE_eatis": 65400,
|
| 138 |
+
"CASE_eatur": 65080,
|
| 139 |
+
"CASE_ebam": 65059,
|
| 140 |
+
"CASE_ebamini": 65433,
|
| 141 |
+
"CASE_ebamur": 65115,
|
| 142 |
+
"CASE_ebamus": 65180,
|
| 143 |
+
"CASE_ebant": 65401,
|
| 144 |
+
"CASE_ebantur": 65136,
|
| 145 |
+
"CASE_ebar": 65342,
|
| 146 |
+
"CASE_ebare": 65049,
|
| 147 |
+
"CASE_ebaris": 65064,
|
| 148 |
+
"CASE_ebas": 65414,
|
| 149 |
+
"CASE_ebat": 65237,
|
| 150 |
+
"CASE_ebatis": 65382,
|
| 151 |
+
"CASE_ebatur": 65111,
|
| 152 |
+
"CASE_ebere": 65031,
|
| 153 |
+
"CASE_eberis": 65381,
|
| 154 |
+
"CASE_ebimur": 65061,
|
| 155 |
+
"CASE_ebimus": 65038,
|
| 156 |
+
"CASE_ebis": 65051,
|
| 157 |
+
"CASE_ebit": 65110,
|
| 158 |
+
"CASE_ebitis": 65162,
|
| 159 |
+
"CASE_ebitur": 65076,
|
| 160 |
+
"CASE_ebo": 65391,
|
| 161 |
+
"CASE_ebor": 65292,
|
| 162 |
+
"CASE_ebunt": 65286,
|
| 163 |
+
"CASE_ebuntur": 65316,
|
| 164 |
+
"CASE_ebus": 65277,
|
| 165 |
+
"CASE_ei": 65325,
|
| 166 |
+
"CASE_eidem": 65301,
|
| 167 |
+
"CASE_eis": 65141,
|
| 168 |
+
"CASE_em": 65339,
|
| 169 |
+
"CASE_eme": 65232,
|
| 170 |
+
"CASE_emini": 65123,
|
| 171 |
+
"CASE_emur": 65191,
|
| 172 |
+
"CASE_emus": 65002,
|
| 173 |
+
"CASE_en": 65175,
|
| 174 |
+
"CASE_enda": 65333,
|
| 175 |
+
"CASE_endae": 65118,
|
| 176 |
+
"CASE_endam": 65066,
|
| 177 |
+
"CASE_endarum": 65057,
|
| 178 |
+
"CASE_endas": 65009,
|
| 179 |
+
"CASE_ende": 65086,
|
| 180 |
+
"CASE_endi": 65368,
|
| 181 |
+
"CASE_endis": 65058,
|
| 182 |
+
"CASE_endo": 65182,
|
| 183 |
+
"CASE_endorum": 65425,
|
| 184 |
+
"CASE_endos": 65297,
|
| 185 |
+
"CASE_endum": 65073,
|
| 186 |
+
"CASE_endus": 65361,
|
| 187 |
+
"CASE_ens": 65238,
|
| 188 |
+
"CASE_ent": 65213,
|
| 189 |
+
"CASE_ente": 65030,
|
| 190 |
+
"CASE_entem": 65005,
|
| 191 |
+
"CASE_entes": 65426,
|
| 192 |
+
"CASE_enti": 65020,
|
| 193 |
+
"CASE_entia": 65133,
|
| 194 |
+
"CASE_entibus": 65032,
|
| 195 |
+
"CASE_entis": 65298,
|
| 196 |
+
"CASE_entium": 65094,
|
| 197 |
+
"CASE_ento": 65439,
|
| 198 |
+
"CASE_entum": 65142,
|
| 199 |
+
"CASE_entur": 65392,
|
| 200 |
+
"CASE_enus": 65430,
|
| 201 |
+
"CASE_eo": 65261,
|
| 202 |
+
"CASE_eor": 65130,
|
| 203 |
+
"CASE_er": 65429,
|
| 204 |
+
"CASE_eram": 65366,
|
| 205 |
+
"CASE_eramus": 65420,
|
| 206 |
+
"CASE_erant": 65373,
|
| 207 |
+
"CASE_eras": 65411,
|
| 208 |
+
"CASE_erat": 65294,
|
| 209 |
+
"CASE_eratis": 65386,
|
| 210 |
+
"CASE_ere": 65230,
|
| 211 |
+
"CASE_erem": 65268,
|
| 212 |
+
"CASE_eremini": 65348,
|
| 213 |
+
"CASE_eremur": 65008,
|
| 214 |
+
"CASE_eremus": 65389,
|
| 215 |
+
"CASE_erent": 65120,
|
| 216 |
+
"CASE_erentur": 65374,
|
| 217 |
+
"CASE_erer": 65204,
|
| 218 |
+
"CASE_erere": 65138,
|
| 219 |
+
"CASE_ereris": 65139,
|
| 220 |
+
"CASE_eres": 65344,
|
| 221 |
+
"CASE_eret": 65357,
|
| 222 |
+
"CASE_eretis": 65143,
|
| 223 |
+
"CASE_eretur": 65022,
|
| 224 |
+
"CASE_eri": 65203,
|
| 225 |
+
"CASE_erier": 65405,
|
| 226 |
+
"CASE_erim": 65241,
|
| 227 |
+
"CASE_erimus": 65326,
|
| 228 |
+
"CASE_erint": 65273,
|
| 229 |
+
"CASE_eris": 65402,
|
| 230 |
+
"CASE_erit": 65114,
|
| 231 |
+
"CASE_eritis": 65154,
|
| 232 |
+
"CASE_ero": 65068,
|
| 233 |
+
"CASE_erum": 65287,
|
| 234 |
+
"CASE_erunt": 65067,
|
| 235 |
+
"CASE_es": 65107,
|
| 236 |
+
"CASE_ese": 65320,
|
| 237 |
+
"CASE_esse": 65216,
|
| 238 |
+
"CASE_essem": 65281,
|
| 239 |
+
"CASE_essemus": 65126,
|
| 240 |
+
"CASE_essent": 65034,
|
| 241 |
+
"CASE_esset": 65251,
|
| 242 |
+
"CASE_est": 65364,
|
| 243 |
+
"CASE_estis": 65157,
|
| 244 |
+
"CASE_esto": 65071,
|
| 245 |
+
"CASE_et": 65014,
|
| 246 |
+
"CASE_ete": 65171,
|
| 247 |
+
"CASE_etis": 65089,
|
| 248 |
+
"CASE_eto": 65248,
|
| 249 |
+
"CASE_etor": 65125,
|
| 250 |
+
"CASE_etote": 65220,
|
| 251 |
+
"CASE_etur": 65380,
|
| 252 |
+
"CASE_fore": 65017,
|
| 253 |
+
"CASE_forent": 65078,
|
| 254 |
+
"CASE_foret": 65212,
|
| 255 |
+
"CASE_germanus": 65424,
|
| 256 |
+
"CASE_i": 65334,
|
| 257 |
+
"CASE_ia": 65159,
|
| 258 |
+
"CASE_iant": 65201,
|
| 259 |
+
"CASE_ias": 65218,
|
| 260 |
+
"CASE_iat": 65322,
|
| 261 |
+
"CASE_ibe": 65099,
|
| 262 |
+
"CASE_ibi": 65161,
|
| 263 |
+
"CASE_ibus": 65081,
|
| 264 |
+
"CASE_ic": 65415,
|
| 265 |
+
"CASE_id": 65035,
|
| 266 |
+
"CASE_iens": 65039,
|
| 267 |
+
"CASE_ier": 65367,
|
| 268 |
+
"CASE_ieri": 65129,
|
| 269 |
+
"CASE_ies": 65253,
|
| 270 |
+
"CASE_ihi": 65422,
|
| 271 |
+
"CASE_ii": 65178,
|
| 272 |
+
"CASE_illa": 65305,
|
| 273 |
+
"CASE_ille": 65043,
|
| 274 |
+
"CASE_im": 65183,
|
| 275 |
+
"CASE_imini": 65007,
|
| 276 |
+
"CASE_imur": 65092,
|
| 277 |
+
"CASE_imus": 65442,
|
| 278 |
+
"CASE_int": 65299,
|
| 279 |
+
"CASE_ipsius": 65385,
|
| 280 |
+
"CASE_ire": 65283,
|
| 281 |
+
"CASE_irem": 65128,
|
| 282 |
+
"CASE_iremini": 65352,
|
| 283 |
+
"CASE_iremur": 65065,
|
| 284 |
+
"CASE_iremus": 65345,
|
| 285 |
+
"CASE_irent": 65384,
|
| 286 |
+
"CASE_irentur": 65328,
|
| 287 |
+
"CASE_irer": 65252,
|
| 288 |
+
"CASE_irere": 65412,
|
| 289 |
+
"CASE_ireris": 65226,
|
| 290 |
+
"CASE_ires": 65335,
|
| 291 |
+
"CASE_iret": 65243,
|
| 292 |
+
"CASE_iretis": 65314,
|
| 293 |
+
"CASE_iretur": 65431,
|
| 294 |
+
"CASE_iri": 65269,
|
| 295 |
+
"CASE_irier": 65101,
|
| 296 |
+
"CASE_iris": 65257,
|
| 297 |
+
"CASE_is": 65158,
|
| 298 |
+
"CASE_isse": 65151,
|
| 299 |
+
"CASE_issem": 65108,
|
| 300 |
+
"CASE_issemus": 65397,
|
| 301 |
+
"CASE_issent": 65330,
|
| 302 |
+
"CASE_isses": 65150,
|
| 303 |
+
"CASE_isset": 65423,
|
| 304 |
+
"CASE_issetis": 65010,
|
| 305 |
+
"CASE_isti": 65428,
|
| 306 |
+
"CASE_istis": 65070,
|
| 307 |
+
"CASE_it": 65096,
|
| 308 |
+
"CASE_ite": 65018,
|
| 309 |
+
"CASE_itis": 65408,
|
| 310 |
+
"CASE_ito": 65388,
|
| 311 |
+
"CASE_itor": 65165,
|
| 312 |
+
"CASE_itote": 65378,
|
| 313 |
+
"CASE_itur": 65097,
|
| 314 |
+
"CASE_ium": 65103,
|
| 315 |
+
"CASE_ius": 65021,
|
| 316 |
+
"CASE_jus": 65176,
|
| 317 |
+
"CASE_latuit": 65418,
|
| 318 |
+
"CASE_le": 65371,
|
| 319 |
+
"CASE_lem": 65055,
|
| 320 |
+
"CASE_lent": 65240,
|
| 321 |
+
"CASE_les": 65360,
|
| 322 |
+
"CASE_let": 65194,
|
| 323 |
+
"CASE_litore": 65289,
|
| 324 |
+
"CASE_ma": 65116,
|
| 325 |
+
"CASE_mae": 65271,
|
| 326 |
+
"CASE_maerens": 65012,
|
| 327 |
+
"CASE_magistratu": 65346,
|
| 328 |
+
"CASE_mam": 65144,
|
| 329 |
+
"CASE_marum": 65259,
|
| 330 |
+
"CASE_mas": 65209,
|
| 331 |
+
"CASE_me": 65393,
|
| 332 |
+
"CASE_mi": 65121,
|
| 333 |
+
"CASE_mini": 65338,
|
| 334 |
+
"CASE_mis": 65040,
|
| 335 |
+
"CASE_mo": 65260,
|
| 336 |
+
"CASE_morum": 65036,
|
| 337 |
+
"CASE_mos": 65172,
|
| 338 |
+
"CASE_mum": 65284,
|
| 339 |
+
"CASE_mur": 65164,
|
| 340 |
+
"CASE_mus": 65205,
|
| 341 |
+
"CASE_non": 65383,
|
| 342 |
+
"CASE_o": 65146,
|
| 343 |
+
"CASE_obis": 65417,
|
| 344 |
+
"CASE_obus": 65085,
|
| 345 |
+
"CASE_oc": 65421,
|
| 346 |
+
"CASE_od": 65304,
|
| 347 |
+
"CASE_oe": 65390,
|
| 348 |
+
"CASE_om": 65306,
|
| 349 |
+
"CASE_on": 65293,
|
| 350 |
+
"CASE_or": 65168,
|
| 351 |
+
"CASE_ora": 65310,
|
| 352 |
+
"CASE_ore": 65416,
|
| 353 |
+
"CASE_orem": 65336,
|
| 354 |
+
"CASE_ores": 65196,
|
| 355 |
+
"CASE_ori": 65349,
|
| 356 |
+
"CASE_oribus": 65052,
|
| 357 |
+
"CASE_oris": 65279,
|
| 358 |
+
"CASE_orum": 65437,
|
| 359 |
+
"CASE_orun": 65140,
|
| 360 |
+
"CASE_os": 65262,
|
| 361 |
+
"CASE_pax": 65440,
|
| 362 |
+
"CASE_praeclarior": 65177,
|
| 363 |
+
"CASE_quae": 65149,
|
| 364 |
+
"CASE_qui": 65324,
|
| 365 |
+
"CASE_quod": 65013,
|
| 366 |
+
"CASE_re": 65184,
|
| 367 |
+
"CASE_rem": 65015,
|
| 368 |
+
"CASE_remur": 65242,
|
| 369 |
+
"CASE_remus": 65332,
|
| 370 |
+
"CASE_rent": 65075,
|
| 371 |
+
"CASE_rentur": 65323,
|
| 372 |
+
"CASE_res": 65312,
|
| 373 |
+
"CASE_ret": 65233,
|
| 374 |
+
"CASE_retis": 65406,
|
| 375 |
+
"CASE_retur": 65285,
|
| 376 |
+
"CASE_ri": 65016,
|
| 377 |
+
"CASE_rier": 65266,
|
| 378 |
+
"CASE_ris": 65363,
|
| 379 |
+
"CASE_s": 65236,
|
| 380 |
+
"CASE_se": 65372,
|
| 381 |
+
"CASE_sem": 65117,
|
| 382 |
+
"CASE_semus": 65050,
|
| 383 |
+
"CASE_sent": 65270,
|
| 384 |
+
"CASE_ses": 65309,
|
| 385 |
+
"CASE_set": 65343,
|
| 386 |
+
"CASE_setis": 65331,
|
| 387 |
+
"CASE_t": 65295,
|
| 388 |
+
"CASE_te": 65288,
|
| 389 |
+
"CASE_tis": 65358,
|
| 390 |
+
"CASE_to": 65170,
|
| 391 |
+
"CASE_tote": 65231,
|
| 392 |
+
"CASE_tristis": 65398,
|
| 393 |
+
"CASE_tuo": 65202,
|
| 394 |
+
"CASE_tur": 65003,
|
| 395 |
+
"CASE_u": 65244,
|
| 396 |
+
"CASE_ua": 65179,
|
| 397 |
+
"CASE_ubi": 65395,
|
| 398 |
+
"CASE_ubus": 65072,
|
| 399 |
+
"CASE_ud": 65004,
|
| 400 |
+
"CASE_ui": 65321,
|
| 401 |
+
"CASE_um": 65250,
|
| 402 |
+
"CASE_umus": 65296,
|
| 403 |
+
"CASE_unc": 65088,
|
| 404 |
+
"CASE_unda": 65169,
|
| 405 |
+
"CASE_undae": 65029,
|
| 406 |
+
"CASE_undam": 65048,
|
| 407 |
+
"CASE_undarum": 65224,
|
| 408 |
+
"CASE_undas": 65300,
|
| 409 |
+
"CASE_unde": 65006,
|
| 410 |
+
"CASE_undi": 65438,
|
| 411 |
+
"CASE_undis": 65153,
|
| 412 |
+
"CASE_undo": 65127,
|
| 413 |
+
"CASE_undorum": 65207,
|
| 414 |
+
"CASE_undos": 65033,
|
| 415 |
+
"CASE_undum": 65217,
|
| 416 |
+
"CASE_undus": 65347,
|
| 417 |
+
"CASE_unt": 65026,
|
| 418 |
+
"CASE_unte": 65307,
|
| 419 |
+
"CASE_untem": 65337,
|
| 420 |
+
"CASE_untes": 65181,
|
| 421 |
+
"CASE_unti": 65265,
|
| 422 |
+
"CASE_untia": 65313,
|
| 423 |
+
"CASE_untibus": 65303,
|
| 424 |
+
"CASE_untis": 65046,
|
| 425 |
+
"CASE_untium": 65132,
|
| 426 |
+
"CASE_unto": 65093,
|
| 427 |
+
"CASE_untur": 65147,
|
| 428 |
+
"CASE_ura": 65090,
|
| 429 |
+
"CASE_urae": 65185,
|
| 430 |
+
"CASE_uram": 65443,
|
| 431 |
+
"CASE_urarum": 65152,
|
| 432 |
+
"CASE_uras": 65235,
|
| 433 |
+
"CASE_ure": 65351,
|
| 434 |
+
"CASE_uri": 65167,
|
| 435 |
+
"CASE_uris": 65263,
|
| 436 |
+
"CASE_uro": 65255,
|
| 437 |
+
"CASE_urorum": 65369,
|
| 438 |
+
"CASE_uros": 65173,
|
| 439 |
+
"CASE_urum": 65419,
|
| 440 |
+
"CASE_urus": 65340,
|
| 441 |
+
"CASE_us": 65407,
|
| 442 |
+
"CASE_ut": 65023,
|
| 443 |
+
"CASE_uum": 65113,
|
| 444 |
+
"CASE_vetus": 65042
|
| 445 |
+
}
|
source.spm
CHANGED
|
Binary files a/source.spm and b/source.spm differ
|
|
|
target.spm
CHANGED
|
Binary files a/target.spm and b/target.spm differ
|
|
|
tokenizer_config.json
CHANGED
|
@@ -3,10 +3,10 @@
|
|
| 3 |
"model_max_length": 512,
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"separate_vocabs": false,
|
| 6 |
-
"source_lang": "
|
| 7 |
"sp_model_kwargs": {},
|
| 8 |
"special_tokens_map_file": null,
|
| 9 |
-
"target_lang": "
|
| 10 |
"tokenizer_class": "MarianTokenizer",
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|
|
|
|
| 3 |
"model_max_length": 512,
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"separate_vocabs": false,
|
| 6 |
+
"source_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la",
|
| 7 |
"sp_model_kwargs": {},
|
| 8 |
"special_tokens_map_file": null,
|
| 9 |
+
"target_lang": "en",
|
| 10 |
"tokenizer_class": "MarianTokenizer",
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|