Upload folder using huggingface_hub
Browse files- merges.json +1 -0
- vocabulary.json +259 -0
merges.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"merges": []}
|
vocabulary.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\u0100": 0,
|
| 3 |
+
"\u0101": 1,
|
| 4 |
+
"\u0102": 2,
|
| 5 |
+
"\u0103": 3,
|
| 6 |
+
"\u0104": 4,
|
| 7 |
+
"\u0105": 5,
|
| 8 |
+
"\u0106": 6,
|
| 9 |
+
"\u0107": 7,
|
| 10 |
+
"\u0108": 8,
|
| 11 |
+
"\u0109": 9,
|
| 12 |
+
"\u010a": 10,
|
| 13 |
+
"\u010b": 11,
|
| 14 |
+
"\u010c": 12,
|
| 15 |
+
"\u010d": 13,
|
| 16 |
+
"\u010e": 14,
|
| 17 |
+
"\u010f": 15,
|
| 18 |
+
"\u0110": 16,
|
| 19 |
+
"\u0111": 17,
|
| 20 |
+
"\u0112": 18,
|
| 21 |
+
"\u0113": 19,
|
| 22 |
+
"\u0114": 20,
|
| 23 |
+
"\u0115": 21,
|
| 24 |
+
"\u0116": 22,
|
| 25 |
+
"\u0117": 23,
|
| 26 |
+
"\u0118": 24,
|
| 27 |
+
"\u0119": 25,
|
| 28 |
+
"\u011a": 26,
|
| 29 |
+
"\u011b": 27,
|
| 30 |
+
"\u011c": 28,
|
| 31 |
+
"\u011d": 29,
|
| 32 |
+
"\u011e": 30,
|
| 33 |
+
"\u011f": 31,
|
| 34 |
+
"\u0120": 32,
|
| 35 |
+
"!": 33,
|
| 36 |
+
"\"": 34,
|
| 37 |
+
"#": 35,
|
| 38 |
+
"$": 36,
|
| 39 |
+
"%": 37,
|
| 40 |
+
"&": 38,
|
| 41 |
+
"'": 39,
|
| 42 |
+
"(": 40,
|
| 43 |
+
")": 41,
|
| 44 |
+
"*": 42,
|
| 45 |
+
"+": 43,
|
| 46 |
+
",": 44,
|
| 47 |
+
"-": 45,
|
| 48 |
+
".": 46,
|
| 49 |
+
"/": 47,
|
| 50 |
+
"0": 48,
|
| 51 |
+
"1": 49,
|
| 52 |
+
"2": 50,
|
| 53 |
+
"3": 51,
|
| 54 |
+
"4": 52,
|
| 55 |
+
"5": 53,
|
| 56 |
+
"6": 54,
|
| 57 |
+
"7": 55,
|
| 58 |
+
"8": 56,
|
| 59 |
+
"9": 57,
|
| 60 |
+
":": 58,
|
| 61 |
+
";": 59,
|
| 62 |
+
"<": 60,
|
| 63 |
+
"=": 61,
|
| 64 |
+
">": 62,
|
| 65 |
+
"?": 63,
|
| 66 |
+
"@": 64,
|
| 67 |
+
"A": 65,
|
| 68 |
+
"B": 66,
|
| 69 |
+
"C": 67,
|
| 70 |
+
"D": 68,
|
| 71 |
+
"E": 69,
|
| 72 |
+
"F": 70,
|
| 73 |
+
"G": 71,
|
| 74 |
+
"H": 72,
|
| 75 |
+
"I": 73,
|
| 76 |
+
"J": 74,
|
| 77 |
+
"K": 75,
|
| 78 |
+
"L": 76,
|
| 79 |
+
"M": 77,
|
| 80 |
+
"N": 78,
|
| 81 |
+
"O": 79,
|
| 82 |
+
"P": 80,
|
| 83 |
+
"Q": 81,
|
| 84 |
+
"R": 82,
|
| 85 |
+
"S": 83,
|
| 86 |
+
"T": 84,
|
| 87 |
+
"U": 85,
|
| 88 |
+
"V": 86,
|
| 89 |
+
"W": 87,
|
| 90 |
+
"X": 88,
|
| 91 |
+
"Y": 89,
|
| 92 |
+
"Z": 90,
|
| 93 |
+
"[": 91,
|
| 94 |
+
"\\": 92,
|
| 95 |
+
"]": 93,
|
| 96 |
+
"^": 94,
|
| 97 |
+
"_": 95,
|
| 98 |
+
"`": 96,
|
| 99 |
+
"a": 97,
|
| 100 |
+
"b": 98,
|
| 101 |
+
"c": 99,
|
| 102 |
+
"d": 100,
|
| 103 |
+
"e": 101,
|
| 104 |
+
"f": 102,
|
| 105 |
+
"g": 103,
|
| 106 |
+
"h": 104,
|
| 107 |
+
"i": 105,
|
| 108 |
+
"j": 106,
|
| 109 |
+
"k": 107,
|
| 110 |
+
"l": 108,
|
| 111 |
+
"m": 109,
|
| 112 |
+
"n": 110,
|
| 113 |
+
"o": 111,
|
| 114 |
+
"p": 112,
|
| 115 |
+
"q": 113,
|
| 116 |
+
"r": 114,
|
| 117 |
+
"s": 115,
|
| 118 |
+
"t": 116,
|
| 119 |
+
"u": 117,
|
| 120 |
+
"v": 118,
|
| 121 |
+
"w": 119,
|
| 122 |
+
"x": 120,
|
| 123 |
+
"y": 121,
|
| 124 |
+
"z": 122,
|
| 125 |
+
"{": 123,
|
| 126 |
+
"|": 124,
|
| 127 |
+
"}": 125,
|
| 128 |
+
"~": 126,
|
| 129 |
+
"\u0121": 127,
|
| 130 |
+
"\u0122": 128,
|
| 131 |
+
"\u0123": 129,
|
| 132 |
+
"\u0124": 130,
|
| 133 |
+
"\u0125": 131,
|
| 134 |
+
"\u0126": 132,
|
| 135 |
+
"\u0127": 133,
|
| 136 |
+
"\u0128": 134,
|
| 137 |
+
"\u0129": 135,
|
| 138 |
+
"\u012a": 136,
|
| 139 |
+
"\u012b": 137,
|
| 140 |
+
"\u012c": 138,
|
| 141 |
+
"\u012d": 139,
|
| 142 |
+
"\u012e": 140,
|
| 143 |
+
"\u012f": 141,
|
| 144 |
+
"\u0130": 142,
|
| 145 |
+
"\u0131": 143,
|
| 146 |
+
"\u0132": 144,
|
| 147 |
+
"\u0133": 145,
|
| 148 |
+
"\u0134": 146,
|
| 149 |
+
"\u0135": 147,
|
| 150 |
+
"\u0136": 148,
|
| 151 |
+
"\u0137": 149,
|
| 152 |
+
"\u0138": 150,
|
| 153 |
+
"\u0139": 151,
|
| 154 |
+
"\u013a": 152,
|
| 155 |
+
"\u013b": 153,
|
| 156 |
+
"\u013c": 154,
|
| 157 |
+
"\u013d": 155,
|
| 158 |
+
"\u013e": 156,
|
| 159 |
+
"\u013f": 157,
|
| 160 |
+
"\u0140": 158,
|
| 161 |
+
"\u0141": 159,
|
| 162 |
+
"\u0142": 160,
|
| 163 |
+
"\u00a1": 161,
|
| 164 |
+
"\u00a2": 162,
|
| 165 |
+
"\u00a3": 163,
|
| 166 |
+
"\u00a4": 164,
|
| 167 |
+
"\u00a5": 165,
|
| 168 |
+
"\u00a6": 166,
|
| 169 |
+
"\u00a7": 167,
|
| 170 |
+
"\u00a8": 168,
|
| 171 |
+
"\u00a9": 169,
|
| 172 |
+
"\u00aa": 170,
|
| 173 |
+
"\u00ab": 171,
|
| 174 |
+
"\u00ac": 172,
|
| 175 |
+
"\u0143": 173,
|
| 176 |
+
"\u00ae": 174,
|
| 177 |
+
"\u00af": 175,
|
| 178 |
+
"\u00b0": 176,
|
| 179 |
+
"\u00b1": 177,
|
| 180 |
+
"\u00b2": 178,
|
| 181 |
+
"\u00b3": 179,
|
| 182 |
+
"\u00b4": 180,
|
| 183 |
+
"\u00b5": 181,
|
| 184 |
+
"\u00b6": 182,
|
| 185 |
+
"\u00b7": 183,
|
| 186 |
+
"\u00b8": 184,
|
| 187 |
+
"\u00b9": 185,
|
| 188 |
+
"\u00ba": 186,
|
| 189 |
+
"\u00bb": 187,
|
| 190 |
+
"\u00bc": 188,
|
| 191 |
+
"\u00bd": 189,
|
| 192 |
+
"\u00be": 190,
|
| 193 |
+
"\u00bf": 191,
|
| 194 |
+
"\u00c0": 192,
|
| 195 |
+
"\u00c1": 193,
|
| 196 |
+
"\u00c2": 194,
|
| 197 |
+
"\u00c3": 195,
|
| 198 |
+
"\u00c4": 196,
|
| 199 |
+
"\u00c5": 197,
|
| 200 |
+
"\u00c6": 198,
|
| 201 |
+
"\u00c7": 199,
|
| 202 |
+
"\u00c8": 200,
|
| 203 |
+
"\u00c9": 201,
|
| 204 |
+
"\u00ca": 202,
|
| 205 |
+
"\u00cb": 203,
|
| 206 |
+
"\u00cc": 204,
|
| 207 |
+
"\u00cd": 205,
|
| 208 |
+
"\u00ce": 206,
|
| 209 |
+
"\u00cf": 207,
|
| 210 |
+
"\u00d0": 208,
|
| 211 |
+
"\u00d1": 209,
|
| 212 |
+
"\u00d2": 210,
|
| 213 |
+
"\u00d3": 211,
|
| 214 |
+
"\u00d4": 212,
|
| 215 |
+
"\u00d5": 213,
|
| 216 |
+
"\u00d6": 214,
|
| 217 |
+
"\u00d7": 215,
|
| 218 |
+
"\u00d8": 216,
|
| 219 |
+
"\u00d9": 217,
|
| 220 |
+
"\u00da": 218,
|
| 221 |
+
"\u00db": 219,
|
| 222 |
+
"\u00dc": 220,
|
| 223 |
+
"\u00dd": 221,
|
| 224 |
+
"\u00de": 222,
|
| 225 |
+
"\u00df": 223,
|
| 226 |
+
"\u00e0": 224,
|
| 227 |
+
"\u00e1": 225,
|
| 228 |
+
"\u00e2": 226,
|
| 229 |
+
"\u00e3": 227,
|
| 230 |
+
"\u00e4": 228,
|
| 231 |
+
"\u00e5": 229,
|
| 232 |
+
"\u00e6": 230,
|
| 233 |
+
"\u00e7": 231,
|
| 234 |
+
"\u00e8": 232,
|
| 235 |
+
"\u00e9": 233,
|
| 236 |
+
"\u00ea": 234,
|
| 237 |
+
"\u00eb": 235,
|
| 238 |
+
"\u00ec": 236,
|
| 239 |
+
"\u00ed": 237,
|
| 240 |
+
"\u00ee": 238,
|
| 241 |
+
"\u00ef": 239,
|
| 242 |
+
"\u00f0": 240,
|
| 243 |
+
"\u00f1": 241,
|
| 244 |
+
"\u00f2": 242,
|
| 245 |
+
"\u00f3": 243,
|
| 246 |
+
"\u00f4": 244,
|
| 247 |
+
"\u00f5": 245,
|
| 248 |
+
"\u00f6": 246,
|
| 249 |
+
"\u00f7": 247,
|
| 250 |
+
"\u00f8": 248,
|
| 251 |
+
"\u00f9": 249,
|
| 252 |
+
"\u00fa": 250,
|
| 253 |
+
"\u00fb": 251,
|
| 254 |
+
"\u00fc": 252,
|
| 255 |
+
"\u00fd": 253,
|
| 256 |
+
"\u00fe": 254,
|
| 257 |
+
"\u00ff": 255,
|
| 258 |
+
"[EOS]": 256
|
| 259 |
+
}
|