Upload folder using huggingface_hub
Browse files- config.json +1 -0
- vocab.json +262 -0
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"pattern": "'(?i:[sdmt]|ll|ve|re)|[^\\r\\n\\p{L}\\p{N}]?+\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]++[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+", "vocab_size": 388}
|
vocab.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\u0000": 0,
|
| 3 |
+
"\u0001": 1,
|
| 4 |
+
"\u0002": 2,
|
| 5 |
+
"\u0003": 3,
|
| 6 |
+
"\u0004": 4,
|
| 7 |
+
"\u0005": 5,
|
| 8 |
+
"\u0006": 6,
|
| 9 |
+
"\u0007": 7,
|
| 10 |
+
"\b": 8,
|
| 11 |
+
"\t": 9,
|
| 12 |
+
"\n": 10,
|
| 13 |
+
"\u000b": 11,
|
| 14 |
+
"\f": 12,
|
| 15 |
+
"\r": 13,
|
| 16 |
+
"\u000e": 14,
|
| 17 |
+
"\u000f": 15,
|
| 18 |
+
"\u0010": 16,
|
| 19 |
+
"\u0011": 17,
|
| 20 |
+
"\u0012": 18,
|
| 21 |
+
"\u0013": 19,
|
| 22 |
+
"\u0014": 20,
|
| 23 |
+
"\u0015": 21,
|
| 24 |
+
"\u0016": 22,
|
| 25 |
+
"\u0017": 23,
|
| 26 |
+
"\u0018": 24,
|
| 27 |
+
"\u0019": 25,
|
| 28 |
+
"\u001a": 26,
|
| 29 |
+
"\u001b": 27,
|
| 30 |
+
"\u001c": 28,
|
| 31 |
+
"\u001d": 29,
|
| 32 |
+
"\u001e": 30,
|
| 33 |
+
"\u001f": 31,
|
| 34 |
+
" ": 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 |
+
"\u007f": 127,
|
| 130 |
+
"\ufffd": 256,
|
| 131 |
+
".\ufffd": 257,
|
| 132 |
+
"..": 258,
|
| 133 |
+
" b": 259,
|
| 134 |
+
" w": 260,
|
| 135 |
+
".x": 261,
|
| 136 |
+
".\u265f": 262,
|
| 137 |
+
".\u2659": 263,
|
| 138 |
+
"\u265f": 264,
|
| 139 |
+
"\u2659": 265,
|
| 140 |
+
"\u2656": 266,
|
| 141 |
+
"\u265c": 267,
|
| 142 |
+
"\u2658": 268,
|
| 143 |
+
".\u2658": 269,
|
| 144 |
+
"\u265e": 270,
|
| 145 |
+
".\u265e": 271,
|
| 146 |
+
".\u2656": 272,
|
| 147 |
+
".\u265c": 273,
|
| 148 |
+
"\u2657": 274,
|
| 149 |
+
".\u2657": 275,
|
| 150 |
+
"\u265d": 276,
|
| 151 |
+
".\u265d": 277,
|
| 152 |
+
"\u265a": 278,
|
| 153 |
+
".\u265a": 279,
|
| 154 |
+
"\u2654": 280,
|
| 155 |
+
".\u2654": 281,
|
| 156 |
+
"\u2655": 282,
|
| 157 |
+
".\u2655": 283,
|
| 158 |
+
"\u265b": 284,
|
| 159 |
+
".\u265b": 285,
|
| 160 |
+
"..+": 286,
|
| 161 |
+
"\u265fd": 287,
|
| 162 |
+
"\u2659d": 288,
|
| 163 |
+
"\u2659e": 289,
|
| 164 |
+
"\u265fe": 290,
|
| 165 |
+
"\u265ag": 291,
|
| 166 |
+
"\u2654g": 292,
|
| 167 |
+
"\u265ef": 293,
|
| 168 |
+
"\u2658f": 294,
|
| 169 |
+
"\u265fc": 295,
|
| 170 |
+
"\u2656d": 296,
|
| 171 |
+
"\u2656f": 297,
|
| 172 |
+
"\u265cf": 298,
|
| 173 |
+
"\u265ed": 299,
|
| 174 |
+
"\u2659c": 300,
|
| 175 |
+
"\u2658d": 301,
|
| 176 |
+
"\u2658c": 302,
|
| 177 |
+
"\u265cd": 303,
|
| 178 |
+
".+": 304,
|
| 179 |
+
"\u265ec": 305,
|
| 180 |
+
"\u2656e": 306,
|
| 181 |
+
"\u2658e": 307,
|
| 182 |
+
"\u2657e": 308,
|
| 183 |
+
"\u265ee": 309,
|
| 184 |
+
"\u265de": 310,
|
| 185 |
+
"\u2659g": 311,
|
| 186 |
+
"\u2659f": 312,
|
| 187 |
+
"\u265cc": 313,
|
| 188 |
+
"\u265fg": 314,
|
| 189 |
+
"\u265fb": 315,
|
| 190 |
+
"\u265ce": 316,
|
| 191 |
+
"\u265ch": 317,
|
| 192 |
+
"\u2656h": 318,
|
| 193 |
+
"\u2657d": 319,
|
| 194 |
+
"\u2656c": 320,
|
| 195 |
+
"\u2659b": 321,
|
| 196 |
+
"\u265ff": 322,
|
| 197 |
+
"\u265dd": 323,
|
| 198 |
+
"\u2659h": 324,
|
| 199 |
+
"\u265fa": 325,
|
| 200 |
+
"\u2655d": 326,
|
| 201 |
+
"\u265af": 327,
|
| 202 |
+
"\u2659a": 328,
|
| 203 |
+
"\u265fh": 329,
|
| 204 |
+
"\u2654f": 330,
|
| 205 |
+
"\u2657f": 331,
|
| 206 |
+
"\u2655e": 332,
|
| 207 |
+
"\u2657g": 333,
|
| 208 |
+
"\u265bd": 334,
|
| 209 |
+
"\u265dg": 335,
|
| 210 |
+
"\u265df": 336,
|
| 211 |
+
"\u265bc": 337,
|
| 212 |
+
"\u265cb": 338,
|
| 213 |
+
"\u2657c": 339,
|
| 214 |
+
"\u2656a": 340,
|
| 215 |
+
"\u265ca": 341,
|
| 216 |
+
"\u265be": 342,
|
| 217 |
+
"\u2656b": 343,
|
| 218 |
+
"\u265dc": 344,
|
| 219 |
+
"\u265ae": 345,
|
| 220 |
+
"\u265db": 346,
|
| 221 |
+
"\u2655c": 347,
|
| 222 |
+
"\u2654e": 348,
|
| 223 |
+
"\u2657b": 349,
|
| 224 |
+
"\u2655f": 350,
|
| 225 |
+
"\u265bb": 351,
|
| 226 |
+
"\u265ah": 352,
|
| 227 |
+
"\u2654h": 353,
|
| 228 |
+
"\u265ad": 354,
|
| 229 |
+
"\u265bf": 355,
|
| 230 |
+
"\u2654d": 356,
|
| 231 |
+
"\u2654c": 357,
|
| 232 |
+
"\u2655b": 358,
|
| 233 |
+
"\u265cg": 359,
|
| 234 |
+
"\u2656g": 360,
|
| 235 |
+
"\u265ac": 361,
|
| 236 |
+
"\u265eb": 362,
|
| 237 |
+
"\u2658g": 363,
|
| 238 |
+
"\u2655g": 364,
|
| 239 |
+
"\u2658b": 365,
|
| 240 |
+
"\u265eg": 366,
|
| 241 |
+
"\u265ba": 367,
|
| 242 |
+
"\u265bg": 368,
|
| 243 |
+
"\u2655h": 369,
|
| 244 |
+
"\u2654b": 370,
|
| 245 |
+
"\u2657h": 371,
|
| 246 |
+
"\u2655a": 372,
|
| 247 |
+
"\u265bh": 373,
|
| 248 |
+
"\u265da": 374,
|
| 249 |
+
"\u265ea": 375,
|
| 250 |
+
"\u265ab": 376,
|
| 251 |
+
"\u2657a": 377,
|
| 252 |
+
"\u265dh": 378,
|
| 253 |
+
"\u265eh": 379,
|
| 254 |
+
"\u2658a": 380,
|
| 255 |
+
"\u2658h": 381,
|
| 256 |
+
"\u2654a": 382,
|
| 257 |
+
"\u265aa": 383,
|
| 258 |
+
"..+#": 384,
|
| 259 |
+
"*.": 385,
|
| 260 |
+
".+#": 386,
|
| 261 |
+
"*.+": 387
|
| 262 |
+
}
|