Upload tokenizer
Browse files- tokenizer.json +254 -254
tokenizer.json
CHANGED
|
@@ -47,260 +47,260 @@
|
|
| 47 |
"\u0006": 7,
|
| 48 |
"\u0007": 8,
|
| 49 |
"\b": 9,
|
| 50 |
-
"\
|
| 51 |
-
"\
|
| 52 |
-
"\
|
| 53 |
-
"\
|
| 54 |
-
"\
|
| 55 |
-
"\
|
| 56 |
-
"\
|
| 57 |
-
"\
|
| 58 |
-
"\
|
| 59 |
-
"\
|
| 60 |
-
"\
|
| 61 |
-
"\
|
| 62 |
-
"\
|
| 63 |
-
"\
|
| 64 |
-
"
|
| 65 |
-
"\"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"
|
| 203 |
-
"
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
| 220 |
-
"
|
| 221 |
-
"
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"
|
| 226 |
-
"
|
| 227 |
-
"
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"
|
| 232 |
-
"
|
| 233 |
-
"
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"
|
| 251 |
-
"
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
| 258 |
-
"
|
| 259 |
-
"
|
| 260 |
-
"
|
| 261 |
-
"
|
| 262 |
-
"
|
| 263 |
-
"
|
| 264 |
-
"
|
| 265 |
-
"
|
| 266 |
-
"
|
| 267 |
-
"
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"
|
| 275 |
-
"
|
| 276 |
-
"
|
| 277 |
-
"
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
| 281 |
-
"
|
| 282 |
-
"
|
| 283 |
-
"
|
| 284 |
-
"
|
| 285 |
-
"
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
| 290 |
-
"
|
| 291 |
-
"
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
| 295 |
-
"
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
"
|
| 303 |
-
"
|
| 304 |
},
|
| 305 |
"merges": []
|
| 306 |
}
|
|
|
|
| 47 |
"\u0006": 7,
|
| 48 |
"\u0007": 8,
|
| 49 |
"\b": 9,
|
| 50 |
+
"\t": 10,
|
| 51 |
+
"\n": 11,
|
| 52 |
+
"\u000b": 12,
|
| 53 |
+
"\f": 13,
|
| 54 |
+
"\r": 14,
|
| 55 |
+
"\u000e": 15,
|
| 56 |
+
"\u000f": 16,
|
| 57 |
+
"\u0010": 17,
|
| 58 |
+
"\u0011": 18,
|
| 59 |
+
"\u0012": 19,
|
| 60 |
+
"\u0013": 20,
|
| 61 |
+
"\u0014": 21,
|
| 62 |
+
"\u0015": 22,
|
| 63 |
+
"\u0016": 23,
|
| 64 |
+
"\u0017": 24,
|
| 65 |
+
"\u0018": 25,
|
| 66 |
+
"\u0019": 26,
|
| 67 |
+
"\u001a": 27,
|
| 68 |
+
"\u001b": 28,
|
| 69 |
+
"\u001c": 29,
|
| 70 |
+
"\u001d": 30,
|
| 71 |
+
"\u001e": 31,
|
| 72 |
+
"\u001f": 32,
|
| 73 |
+
" ": 33,
|
| 74 |
+
"!": 34,
|
| 75 |
+
"\"": 35,
|
| 76 |
+
"#": 36,
|
| 77 |
+
"$": 37,
|
| 78 |
+
"%": 38,
|
| 79 |
+
"&": 39,
|
| 80 |
+
"'": 40,
|
| 81 |
+
"(": 41,
|
| 82 |
+
")": 42,
|
| 83 |
+
"*": 43,
|
| 84 |
+
"+": 44,
|
| 85 |
+
",": 45,
|
| 86 |
+
"-": 46,
|
| 87 |
+
".": 47,
|
| 88 |
+
"/": 48,
|
| 89 |
+
"0": 49,
|
| 90 |
+
"1": 50,
|
| 91 |
+
"2": 51,
|
| 92 |
+
"3": 52,
|
| 93 |
+
"4": 53,
|
| 94 |
+
"5": 54,
|
| 95 |
+
"6": 55,
|
| 96 |
+
"7": 56,
|
| 97 |
+
"8": 57,
|
| 98 |
+
"9": 58,
|
| 99 |
+
":": 59,
|
| 100 |
+
";": 60,
|
| 101 |
+
"<": 61,
|
| 102 |
+
"=": 62,
|
| 103 |
+
">": 63,
|
| 104 |
+
"?": 64,
|
| 105 |
+
"@": 65,
|
| 106 |
+
"A": 66,
|
| 107 |
+
"B": 67,
|
| 108 |
+
"C": 68,
|
| 109 |
+
"D": 69,
|
| 110 |
+
"E": 70,
|
| 111 |
+
"F": 71,
|
| 112 |
+
"G": 72,
|
| 113 |
+
"H": 73,
|
| 114 |
+
"I": 74,
|
| 115 |
+
"J": 75,
|
| 116 |
+
"K": 76,
|
| 117 |
+
"L": 77,
|
| 118 |
+
"M": 78,
|
| 119 |
+
"N": 79,
|
| 120 |
+
"O": 80,
|
| 121 |
+
"P": 81,
|
| 122 |
+
"Q": 82,
|
| 123 |
+
"R": 83,
|
| 124 |
+
"S": 84,
|
| 125 |
+
"T": 85,
|
| 126 |
+
"U": 86,
|
| 127 |
+
"V": 87,
|
| 128 |
+
"W": 88,
|
| 129 |
+
"X": 89,
|
| 130 |
+
"Y": 90,
|
| 131 |
+
"Z": 91,
|
| 132 |
+
"[": 92,
|
| 133 |
+
"\\": 93,
|
| 134 |
+
"]": 94,
|
| 135 |
+
"^": 95,
|
| 136 |
+
"_": 96,
|
| 137 |
+
"`": 97,
|
| 138 |
+
"a": 98,
|
| 139 |
+
"b": 99,
|
| 140 |
+
"c": 100,
|
| 141 |
+
"d": 101,
|
| 142 |
+
"e": 102,
|
| 143 |
+
"f": 103,
|
| 144 |
+
"g": 104,
|
| 145 |
+
"h": 105,
|
| 146 |
+
"i": 106,
|
| 147 |
+
"j": 107,
|
| 148 |
+
"k": 108,
|
| 149 |
+
"l": 109,
|
| 150 |
+
"m": 110,
|
| 151 |
+
"n": 111,
|
| 152 |
+
"o": 112,
|
| 153 |
+
"p": 113,
|
| 154 |
+
"q": 114,
|
| 155 |
+
"r": 115,
|
| 156 |
+
"s": 116,
|
| 157 |
+
"t": 117,
|
| 158 |
+
"u": 118,
|
| 159 |
+
"v": 119,
|
| 160 |
+
"w": 120,
|
| 161 |
+
"x": 121,
|
| 162 |
+
"y": 122,
|
| 163 |
+
"z": 123,
|
| 164 |
+
"{": 124,
|
| 165 |
+
"|": 125,
|
| 166 |
+
"}": 126,
|
| 167 |
+
"~": 127,
|
| 168 |
+
"": 128,
|
| 169 |
+
"": 129,
|
| 170 |
+
"": 130,
|
| 171 |
+
"": 131,
|
| 172 |
+
"": 132,
|
| 173 |
+
"": 133,
|
| 174 |
+
"
": 134,
|
| 175 |
+
"": 135,
|
| 176 |
+
"": 136,
|
| 177 |
+
"": 137,
|
| 178 |
+
"": 138,
|
| 179 |
+
"": 139,
|
| 180 |
+
"": 140,
|
| 181 |
+
"": 141,
|
| 182 |
+
"": 142,
|
| 183 |
+
"": 143,
|
| 184 |
+
"": 144,
|
| 185 |
+
"": 145,
|
| 186 |
+
"": 146,
|
| 187 |
+
"": 147,
|
| 188 |
+
"": 148,
|
| 189 |
+
"": 149,
|
| 190 |
+
"": 150,
|
| 191 |
+
"": 151,
|
| 192 |
+
"": 152,
|
| 193 |
+
"": 153,
|
| 194 |
+
"": 154,
|
| 195 |
+
"": 155,
|
| 196 |
+
"": 156,
|
| 197 |
+
"": 157,
|
| 198 |
+
"": 158,
|
| 199 |
+
"": 159,
|
| 200 |
+
"": 160,
|
| 201 |
+
" ": 161,
|
| 202 |
+
"¡": 162,
|
| 203 |
+
"¢": 163,
|
| 204 |
+
"£": 164,
|
| 205 |
+
"¤": 165,
|
| 206 |
+
"¥": 166,
|
| 207 |
+
"¦": 167,
|
| 208 |
+
"§": 168,
|
| 209 |
+
"¨": 169,
|
| 210 |
+
"©": 170,
|
| 211 |
+
"ª": 171,
|
| 212 |
+
"«": 172,
|
| 213 |
+
"¬": 173,
|
| 214 |
+
"": 174,
|
| 215 |
+
"®": 175,
|
| 216 |
+
"¯": 176,
|
| 217 |
+
"°": 177,
|
| 218 |
+
"±": 178,
|
| 219 |
+
"²": 179,
|
| 220 |
+
"³": 180,
|
| 221 |
+
"´": 181,
|
| 222 |
+
"µ": 182,
|
| 223 |
+
"¶": 183,
|
| 224 |
+
"·": 184,
|
| 225 |
+
"¸": 185,
|
| 226 |
+
"¹": 186,
|
| 227 |
+
"º": 187,
|
| 228 |
+
"»": 188,
|
| 229 |
+
"¼": 189,
|
| 230 |
+
"½": 190,
|
| 231 |
+
"¾": 191,
|
| 232 |
+
"¿": 192,
|
| 233 |
+
"À": 193,
|
| 234 |
+
"Á": 194,
|
| 235 |
+
"Â": 195,
|
| 236 |
+
"Ã": 196,
|
| 237 |
+
"Ä": 197,
|
| 238 |
+
"Å": 198,
|
| 239 |
+
"Æ": 199,
|
| 240 |
+
"Ç": 200,
|
| 241 |
+
"È": 201,
|
| 242 |
+
"É": 202,
|
| 243 |
+
"Ê": 203,
|
| 244 |
+
"Ë": 204,
|
| 245 |
+
"Ì": 205,
|
| 246 |
+
"Í": 206,
|
| 247 |
+
"Î": 207,
|
| 248 |
+
"Ï": 208,
|
| 249 |
+
"Ð": 209,
|
| 250 |
+
"Ñ": 210,
|
| 251 |
+
"Ò": 211,
|
| 252 |
+
"Ó": 212,
|
| 253 |
+
"Ô": 213,
|
| 254 |
+
"Õ": 214,
|
| 255 |
+
"Ö": 215,
|
| 256 |
+
"×": 216,
|
| 257 |
+
"Ø": 217,
|
| 258 |
+
"Ù": 218,
|
| 259 |
+
"Ú": 219,
|
| 260 |
+
"Û": 220,
|
| 261 |
+
"Ü": 221,
|
| 262 |
+
"Ý": 222,
|
| 263 |
+
"Þ": 223,
|
| 264 |
+
"ß": 224,
|
| 265 |
+
"à": 225,
|
| 266 |
+
"á": 226,
|
| 267 |
+
"â": 227,
|
| 268 |
+
"ã": 228,
|
| 269 |
+
"ä": 229,
|
| 270 |
+
"å": 230,
|
| 271 |
+
"æ": 231,
|
| 272 |
+
"ç": 232,
|
| 273 |
+
"è": 233,
|
| 274 |
+
"é": 234,
|
| 275 |
+
"ê": 235,
|
| 276 |
+
"ë": 236,
|
| 277 |
+
"ì": 237,
|
| 278 |
+
"í": 238,
|
| 279 |
+
"î": 239,
|
| 280 |
+
"ï": 240,
|
| 281 |
+
"ð": 241,
|
| 282 |
+
"ñ": 242,
|
| 283 |
+
"ò": 243,
|
| 284 |
+
"ó": 244,
|
| 285 |
+
"ô": 245,
|
| 286 |
+
"õ": 246,
|
| 287 |
+
"ö": 247,
|
| 288 |
+
"÷": 248,
|
| 289 |
+
"ø": 249,
|
| 290 |
+
"ù": 250,
|
| 291 |
+
"ú": 251,
|
| 292 |
+
"û": 252,
|
| 293 |
+
"ü": 253,
|
| 294 |
+
"ý": 254,
|
| 295 |
+
"þ": 255,
|
| 296 |
+
"ÿ": 256,
|
| 297 |
+
"Ā": 257,
|
| 298 |
+
"ā": 258,
|
| 299 |
+
"Ă": 259,
|
| 300 |
+
"ă": 260,
|
| 301 |
+
"Ą": 261,
|
| 302 |
+
"ą": 262,
|
| 303 |
+
"Ć": 263
|
| 304 |
},
|
| 305 |
"merges": []
|
| 306 |
}
|