Upload tokenizer
Browse files- tokenizer.json +147 -43
tokenizer.json
CHANGED
|
@@ -113,38 +113,58 @@
|
|
| 113 |
"\n": 8,
|
| 114 |
"?": 9,
|
| 115 |
"F": 10,
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
"an": 31,
|
| 137 |
"ex": 32,
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"▁
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
},
|
| 149 |
"merges": [
|
| 150 |
[
|
|
@@ -155,6 +175,10 @@
|
|
| 155 |
"t",
|
| 156 |
"he"
|
| 157 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
[
|
| 159 |
"a",
|
| 160 |
"n"
|
|
@@ -163,18 +187,10 @@
|
|
| 163 |
"e",
|
| 164 |
"x"
|
| 165 |
],
|
| 166 |
-
[
|
| 167 |
-
"i",
|
| 168 |
-
"s"
|
| 169 |
-
],
|
| 170 |
[
|
| 171 |
"m",
|
| 172 |
"e"
|
| 173 |
],
|
| 174 |
-
[
|
| 175 |
-
"o",
|
| 176 |
-
"the"
|
| 177 |
-
],
|
| 178 |
[
|
| 179 |
"o",
|
| 180 |
"me"
|
|
@@ -187,21 +203,109 @@
|
|
| 187 |
"t",
|
| 188 |
"ex"
|
| 189 |
],
|
| 190 |
-
[
|
| 191 |
-
"▁",
|
| 192 |
-
"some"
|
| 193 |
-
],
|
| 194 |
[
|
| 195 |
"▁",
|
| 196 |
"tex"
|
| 197 |
],
|
| 198 |
[
|
| 199 |
-
"
|
| 200 |
"r"
|
| 201 |
],
|
| 202 |
[
|
| 203 |
"▁tex",
|
| 204 |
"t"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
]
|
| 206 |
]
|
| 207 |
}
|
|
|
|
| 113 |
"\n": 8,
|
| 114 |
"?": 9,
|
| 115 |
"F": 10,
|
| 116 |
+
"W": 11,
|
| 117 |
+
"a": 12,
|
| 118 |
+
"c": 13,
|
| 119 |
+
"e": 14,
|
| 120 |
+
"f": 15,
|
| 121 |
+
"h": 16,
|
| 122 |
+
"i": 17,
|
| 123 |
+
"l": 18,
|
| 124 |
+
"m": 19,
|
| 125 |
+
"n": 20,
|
| 126 |
+
"o": 21,
|
| 127 |
+
"p": 22,
|
| 128 |
+
"r": 23,
|
| 129 |
+
"s": 24,
|
| 130 |
+
"t": 25,
|
| 131 |
+
"x": 26,
|
| 132 |
+
"▁": 27,
|
| 133 |
+
"he": 28,
|
| 134 |
+
"the": 29,
|
| 135 |
+
"▁o": 30,
|
| 136 |
"an": 31,
|
| 137 |
"ex": 32,
|
| 138 |
+
"me": 33,
|
| 139 |
+
"ome": 34,
|
| 140 |
+
"some": 35,
|
| 141 |
+
"tex": 36,
|
| 142 |
+
"▁tex": 37,
|
| 143 |
+
"ther": 38,
|
| 144 |
+
"▁text": 39,
|
| 145 |
+
"Fr": 40,
|
| 146 |
+
"Wh": 41,
|
| 147 |
+
"al": 42,
|
| 148 |
+
"ap": 43,
|
| 149 |
+
"at": 44,
|
| 150 |
+
"ce": 45,
|
| 151 |
+
"cap": 46,
|
| 152 |
+
"is": 47,
|
| 153 |
+
"it": 48,
|
| 154 |
+
"▁the": 49,
|
| 155 |
+
"▁some": 50,
|
| 156 |
+
"▁Fr": 51,
|
| 157 |
+
"▁Wh": 52,
|
| 158 |
+
"▁cap": 53,
|
| 159 |
+
"▁is": 54,
|
| 160 |
+
"▁of": 55,
|
| 161 |
+
"▁other": 56,
|
| 162 |
+
"ance": 57,
|
| 163 |
+
"ital": 58,
|
| 164 |
+
"▁France": 59,
|
| 165 |
+
"▁What": 60,
|
| 166 |
+
"▁capital": 61,
|
| 167 |
+
"▁France?": 62
|
| 168 |
},
|
| 169 |
"merges": [
|
| 170 |
[
|
|
|
|
| 175 |
"t",
|
| 176 |
"he"
|
| 177 |
],
|
| 178 |
+
[
|
| 179 |
+
"▁",
|
| 180 |
+
"o"
|
| 181 |
+
],
|
| 182 |
[
|
| 183 |
"a",
|
| 184 |
"n"
|
|
|
|
| 187 |
"e",
|
| 188 |
"x"
|
| 189 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
[
|
| 191 |
"m",
|
| 192 |
"e"
|
| 193 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
[
|
| 195 |
"o",
|
| 196 |
"me"
|
|
|
|
| 203 |
"t",
|
| 204 |
"ex"
|
| 205 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
[
|
| 207 |
"▁",
|
| 208 |
"tex"
|
| 209 |
],
|
| 210 |
[
|
| 211 |
+
"the",
|
| 212 |
"r"
|
| 213 |
],
|
| 214 |
[
|
| 215 |
"▁tex",
|
| 216 |
"t"
|
| 217 |
+
],
|
| 218 |
+
[
|
| 219 |
+
"F",
|
| 220 |
+
"r"
|
| 221 |
+
],
|
| 222 |
+
[
|
| 223 |
+
"W",
|
| 224 |
+
"h"
|
| 225 |
+
],
|
| 226 |
+
[
|
| 227 |
+
"a",
|
| 228 |
+
"l"
|
| 229 |
+
],
|
| 230 |
+
[
|
| 231 |
+
"a",
|
| 232 |
+
"p"
|
| 233 |
+
],
|
| 234 |
+
[
|
| 235 |
+
"a",
|
| 236 |
+
"t"
|
| 237 |
+
],
|
| 238 |
+
[
|
| 239 |
+
"c",
|
| 240 |
+
"e"
|
| 241 |
+
],
|
| 242 |
+
[
|
| 243 |
+
"c",
|
| 244 |
+
"ap"
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
"i",
|
| 248 |
+
"s"
|
| 249 |
+
],
|
| 250 |
+
[
|
| 251 |
+
"i",
|
| 252 |
+
"t"
|
| 253 |
+
],
|
| 254 |
+
[
|
| 255 |
+
"▁",
|
| 256 |
+
"the"
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
"▁",
|
| 260 |
+
"some"
|
| 261 |
+
],
|
| 262 |
+
[
|
| 263 |
+
"▁",
|
| 264 |
+
"Fr"
|
| 265 |
+
],
|
| 266 |
+
[
|
| 267 |
+
"▁",
|
| 268 |
+
"Wh"
|
| 269 |
+
],
|
| 270 |
+
[
|
| 271 |
+
"▁",
|
| 272 |
+
"cap"
|
| 273 |
+
],
|
| 274 |
+
[
|
| 275 |
+
"▁",
|
| 276 |
+
"is"
|
| 277 |
+
],
|
| 278 |
+
[
|
| 279 |
+
"▁o",
|
| 280 |
+
"f"
|
| 281 |
+
],
|
| 282 |
+
[
|
| 283 |
+
"▁o",
|
| 284 |
+
"ther"
|
| 285 |
+
],
|
| 286 |
+
[
|
| 287 |
+
"an",
|
| 288 |
+
"ce"
|
| 289 |
+
],
|
| 290 |
+
[
|
| 291 |
+
"it",
|
| 292 |
+
"al"
|
| 293 |
+
],
|
| 294 |
+
[
|
| 295 |
+
"▁Fr",
|
| 296 |
+
"ance"
|
| 297 |
+
],
|
| 298 |
+
[
|
| 299 |
+
"▁Wh",
|
| 300 |
+
"at"
|
| 301 |
+
],
|
| 302 |
+
[
|
| 303 |
+
"▁cap",
|
| 304 |
+
"ital"
|
| 305 |
+
],
|
| 306 |
+
[
|
| 307 |
+
"▁France",
|
| 308 |
+
"?"
|
| 309 |
]
|
| 310 |
]
|
| 311 |
}
|