Upload folder using huggingface_hub
Browse files- bpe_tokenizer.json +395 -0
- pytorch_model.safetensors +3 -0
bpe_tokenizer.json
ADDED
|
@@ -0,0 +1,395 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[EOS]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": null,
|
| 35 |
+
"pre_tokenizer": {
|
| 36 |
+
"type": "Whitespace"
|
| 37 |
+
},
|
| 38 |
+
"post_processor": null,
|
| 39 |
+
"decoder": null,
|
| 40 |
+
"model": {
|
| 41 |
+
"type": "BPE",
|
| 42 |
+
"dropout": null,
|
| 43 |
+
"unk_token": "[UNK]",
|
| 44 |
+
"continuing_subword_prefix": null,
|
| 45 |
+
"end_of_word_suffix": null,
|
| 46 |
+
"fuse_unk": false,
|
| 47 |
+
"byte_fallback": false,
|
| 48 |
+
"ignore_merges": false,
|
| 49 |
+
"vocab": {
|
| 50 |
+
"[UNK]": 0,
|
| 51 |
+
"[PAD]": 1,
|
| 52 |
+
"[EOS]": 2,
|
| 53 |
+
"a": 3,
|
| 54 |
+
"d": 4,
|
| 55 |
+
"e": 5,
|
| 56 |
+
"f": 6,
|
| 57 |
+
"g": 7,
|
| 58 |
+
"h": 8,
|
| 59 |
+
"i": 9,
|
| 60 |
+
"l": 10,
|
| 61 |
+
"n": 11,
|
| 62 |
+
"o": 12,
|
| 63 |
+
"r": 13,
|
| 64 |
+
"s": 14,
|
| 65 |
+
"t": 15,
|
| 66 |
+
"u": 16,
|
| 67 |
+
"v": 17,
|
| 68 |
+
"w": 18,
|
| 69 |
+
"x": 19,
|
| 70 |
+
"y": 20,
|
| 71 |
+
"nd": 21,
|
| 72 |
+
"and": 22,
|
| 73 |
+
"ty": 23,
|
| 74 |
+
"th": 24,
|
| 75 |
+
"ou": 25,
|
| 76 |
+
"re": 26,
|
| 77 |
+
"sand": 27,
|
| 78 |
+
"thou": 28,
|
| 79 |
+
"thousand": 29,
|
| 80 |
+
"hu": 30,
|
| 81 |
+
"ndre": 31,
|
| 82 |
+
"hundre": 32,
|
| 83 |
+
"hundred": 33,
|
| 84 |
+
"en": 34,
|
| 85 |
+
"ne": 35,
|
| 86 |
+
"ev": 36,
|
| 87 |
+
"even": 37,
|
| 88 |
+
"ei": 38,
|
| 89 |
+
"gh": 39,
|
| 90 |
+
"eigh": 40,
|
| 91 |
+
"tw": 41,
|
| 92 |
+
"seven": 42,
|
| 93 |
+
"fi": 43,
|
| 94 |
+
"ix": 44,
|
| 95 |
+
"six": 45,
|
| 96 |
+
"ine": 46,
|
| 97 |
+
"nine": 47,
|
| 98 |
+
"rty": 48,
|
| 99 |
+
"eight": 49,
|
| 100 |
+
"ve": 50,
|
| 101 |
+
"fou": 51,
|
| 102 |
+
"four": 52,
|
| 103 |
+
"two": 53,
|
| 104 |
+
"one": 54,
|
| 105 |
+
"five": 55,
|
| 106 |
+
"thre": 56,
|
| 107 |
+
"three": 57,
|
| 108 |
+
"thi": 58,
|
| 109 |
+
"fif": 59,
|
| 110 |
+
"sixty": 60,
|
| 111 |
+
"fo": 61,
|
| 112 |
+
"forty": 62,
|
| 113 |
+
"enty": 63,
|
| 114 |
+
"twenty": 64,
|
| 115 |
+
"seventy": 65,
|
| 116 |
+
"thirty": 66,
|
| 117 |
+
"fifty": 67,
|
| 118 |
+
"eighty": 68,
|
| 119 |
+
"ninety": 69,
|
| 120 |
+
"een": 70,
|
| 121 |
+
"teen": 71,
|
| 122 |
+
"el": 72,
|
| 123 |
+
"twel": 73,
|
| 124 |
+
"twelve": 74,
|
| 125 |
+
"rteen": 75,
|
| 126 |
+
"thirteen": 76,
|
| 127 |
+
"fifteen": 77,
|
| 128 |
+
"nineteen": 78,
|
| 129 |
+
"seventeen": 79,
|
| 130 |
+
"eleven": 80,
|
| 131 |
+
"fourteen": 81,
|
| 132 |
+
"eighteen": 82,
|
| 133 |
+
"ten": 83,
|
| 134 |
+
"sixteen": 84
|
| 135 |
+
},
|
| 136 |
+
"merges": [
|
| 137 |
+
[
|
| 138 |
+
"n",
|
| 139 |
+
"d"
|
| 140 |
+
],
|
| 141 |
+
[
|
| 142 |
+
"a",
|
| 143 |
+
"nd"
|
| 144 |
+
],
|
| 145 |
+
[
|
| 146 |
+
"t",
|
| 147 |
+
"y"
|
| 148 |
+
],
|
| 149 |
+
[
|
| 150 |
+
"t",
|
| 151 |
+
"h"
|
| 152 |
+
],
|
| 153 |
+
[
|
| 154 |
+
"o",
|
| 155 |
+
"u"
|
| 156 |
+
],
|
| 157 |
+
[
|
| 158 |
+
"r",
|
| 159 |
+
"e"
|
| 160 |
+
],
|
| 161 |
+
[
|
| 162 |
+
"s",
|
| 163 |
+
"and"
|
| 164 |
+
],
|
| 165 |
+
[
|
| 166 |
+
"th",
|
| 167 |
+
"ou"
|
| 168 |
+
],
|
| 169 |
+
[
|
| 170 |
+
"thou",
|
| 171 |
+
"sand"
|
| 172 |
+
],
|
| 173 |
+
[
|
| 174 |
+
"h",
|
| 175 |
+
"u"
|
| 176 |
+
],
|
| 177 |
+
[
|
| 178 |
+
"nd",
|
| 179 |
+
"re"
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
"hu",
|
| 183 |
+
"ndre"
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
"hundre",
|
| 187 |
+
"d"
|
| 188 |
+
],
|
| 189 |
+
[
|
| 190 |
+
"e",
|
| 191 |
+
"n"
|
| 192 |
+
],
|
| 193 |
+
[
|
| 194 |
+
"n",
|
| 195 |
+
"e"
|
| 196 |
+
],
|
| 197 |
+
[
|
| 198 |
+
"e",
|
| 199 |
+
"v"
|
| 200 |
+
],
|
| 201 |
+
[
|
| 202 |
+
"ev",
|
| 203 |
+
"en"
|
| 204 |
+
],
|
| 205 |
+
[
|
| 206 |
+
"e",
|
| 207 |
+
"i"
|
| 208 |
+
],
|
| 209 |
+
[
|
| 210 |
+
"g",
|
| 211 |
+
"h"
|
| 212 |
+
],
|
| 213 |
+
[
|
| 214 |
+
"ei",
|
| 215 |
+
"gh"
|
| 216 |
+
],
|
| 217 |
+
[
|
| 218 |
+
"t",
|
| 219 |
+
"w"
|
| 220 |
+
],
|
| 221 |
+
[
|
| 222 |
+
"s",
|
| 223 |
+
"even"
|
| 224 |
+
],
|
| 225 |
+
[
|
| 226 |
+
"f",
|
| 227 |
+
"i"
|
| 228 |
+
],
|
| 229 |
+
[
|
| 230 |
+
"i",
|
| 231 |
+
"x"
|
| 232 |
+
],
|
| 233 |
+
[
|
| 234 |
+
"s",
|
| 235 |
+
"ix"
|
| 236 |
+
],
|
| 237 |
+
[
|
| 238 |
+
"i",
|
| 239 |
+
"ne"
|
| 240 |
+
],
|
| 241 |
+
[
|
| 242 |
+
"n",
|
| 243 |
+
"ine"
|
| 244 |
+
],
|
| 245 |
+
[
|
| 246 |
+
"r",
|
| 247 |
+
"ty"
|
| 248 |
+
],
|
| 249 |
+
[
|
| 250 |
+
"eigh",
|
| 251 |
+
"t"
|
| 252 |
+
],
|
| 253 |
+
[
|
| 254 |
+
"v",
|
| 255 |
+
"e"
|
| 256 |
+
],
|
| 257 |
+
[
|
| 258 |
+
"f",
|
| 259 |
+
"ou"
|
| 260 |
+
],
|
| 261 |
+
[
|
| 262 |
+
"fou",
|
| 263 |
+
"r"
|
| 264 |
+
],
|
| 265 |
+
[
|
| 266 |
+
"tw",
|
| 267 |
+
"o"
|
| 268 |
+
],
|
| 269 |
+
[
|
| 270 |
+
"o",
|
| 271 |
+
"ne"
|
| 272 |
+
],
|
| 273 |
+
[
|
| 274 |
+
"fi",
|
| 275 |
+
"ve"
|
| 276 |
+
],
|
| 277 |
+
[
|
| 278 |
+
"th",
|
| 279 |
+
"re"
|
| 280 |
+
],
|
| 281 |
+
[
|
| 282 |
+
"thre",
|
| 283 |
+
"e"
|
| 284 |
+
],
|
| 285 |
+
[
|
| 286 |
+
"th",
|
| 287 |
+
"i"
|
| 288 |
+
],
|
| 289 |
+
[
|
| 290 |
+
"fi",
|
| 291 |
+
"f"
|
| 292 |
+
],
|
| 293 |
+
[
|
| 294 |
+
"six",
|
| 295 |
+
"ty"
|
| 296 |
+
],
|
| 297 |
+
[
|
| 298 |
+
"f",
|
| 299 |
+
"o"
|
| 300 |
+
],
|
| 301 |
+
[
|
| 302 |
+
"fo",
|
| 303 |
+
"rty"
|
| 304 |
+
],
|
| 305 |
+
[
|
| 306 |
+
"en",
|
| 307 |
+
"ty"
|
| 308 |
+
],
|
| 309 |
+
[
|
| 310 |
+
"tw",
|
| 311 |
+
"enty"
|
| 312 |
+
],
|
| 313 |
+
[
|
| 314 |
+
"seven",
|
| 315 |
+
"ty"
|
| 316 |
+
],
|
| 317 |
+
[
|
| 318 |
+
"thi",
|
| 319 |
+
"rty"
|
| 320 |
+
],
|
| 321 |
+
[
|
| 322 |
+
"fif",
|
| 323 |
+
"ty"
|
| 324 |
+
],
|
| 325 |
+
[
|
| 326 |
+
"eigh",
|
| 327 |
+
"ty"
|
| 328 |
+
],
|
| 329 |
+
[
|
| 330 |
+
"nine",
|
| 331 |
+
"ty"
|
| 332 |
+
],
|
| 333 |
+
[
|
| 334 |
+
"e",
|
| 335 |
+
"en"
|
| 336 |
+
],
|
| 337 |
+
[
|
| 338 |
+
"t",
|
| 339 |
+
"een"
|
| 340 |
+
],
|
| 341 |
+
[
|
| 342 |
+
"e",
|
| 343 |
+
"l"
|
| 344 |
+
],
|
| 345 |
+
[
|
| 346 |
+
"tw",
|
| 347 |
+
"el"
|
| 348 |
+
],
|
| 349 |
+
[
|
| 350 |
+
"twel",
|
| 351 |
+
"ve"
|
| 352 |
+
],
|
| 353 |
+
[
|
| 354 |
+
"r",
|
| 355 |
+
"teen"
|
| 356 |
+
],
|
| 357 |
+
[
|
| 358 |
+
"thi",
|
| 359 |
+
"rteen"
|
| 360 |
+
],
|
| 361 |
+
[
|
| 362 |
+
"fif",
|
| 363 |
+
"teen"
|
| 364 |
+
],
|
| 365 |
+
[
|
| 366 |
+
"nine",
|
| 367 |
+
"teen"
|
| 368 |
+
],
|
| 369 |
+
[
|
| 370 |
+
"seven",
|
| 371 |
+
"teen"
|
| 372 |
+
],
|
| 373 |
+
[
|
| 374 |
+
"el",
|
| 375 |
+
"even"
|
| 376 |
+
],
|
| 377 |
+
[
|
| 378 |
+
"four",
|
| 379 |
+
"teen"
|
| 380 |
+
],
|
| 381 |
+
[
|
| 382 |
+
"eight",
|
| 383 |
+
"een"
|
| 384 |
+
],
|
| 385 |
+
[
|
| 386 |
+
"t",
|
| 387 |
+
"en"
|
| 388 |
+
],
|
| 389 |
+
[
|
| 390 |
+
"six",
|
| 391 |
+
"teen"
|
| 392 |
+
]
|
| 393 |
+
]
|
| 394 |
+
}
|
| 395 |
+
}
|
pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b531a7adc3310084e2c1d9047a1e7bf2801891f3b2acf801c145ab34442117f
|
| 3 |
+
size 3322036
|