Add tokenizer files
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +369 -0
- tokenizer_config.json +53 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[BOS]",
|
| 3 |
+
"eos_token": "[EOS]",
|
| 4 |
+
"mask_token": "_",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "_",
|
| 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": "[UNK]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[BOS]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[EOS]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "Sequence",
|
| 54 |
+
"normalizers": [
|
| 55 |
+
{
|
| 56 |
+
"type": "NFD"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"type": "StripAccents"
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"type": "Lowercase"
|
| 63 |
+
}
|
| 64 |
+
]
|
| 65 |
+
},
|
| 66 |
+
"pre_tokenizer": {
|
| 67 |
+
"type": "Whitespace"
|
| 68 |
+
},
|
| 69 |
+
"post_processor": null,
|
| 70 |
+
"decoder": null,
|
| 71 |
+
"model": {
|
| 72 |
+
"type": "WordLevel",
|
| 73 |
+
"vocab": {
|
| 74 |
+
"_": 0,
|
| 75 |
+
"[PAD]": 1,
|
| 76 |
+
"[UNK]": 2,
|
| 77 |
+
"[BOS]": 3,
|
| 78 |
+
"[EOS]": 4,
|
| 79 |
+
"a": 5,
|
| 80 |
+
"b": 6,
|
| 81 |
+
"c": 7,
|
| 82 |
+
"d": 8,
|
| 83 |
+
"e": 9,
|
| 84 |
+
"f": 10,
|
| 85 |
+
"g": 11,
|
| 86 |
+
"h": 12,
|
| 87 |
+
"i": 13,
|
| 88 |
+
"j": 14,
|
| 89 |
+
"k": 15,
|
| 90 |
+
"l": 16,
|
| 91 |
+
"m": 17,
|
| 92 |
+
"n": 18,
|
| 93 |
+
"o": 19,
|
| 94 |
+
"p": 20,
|
| 95 |
+
"q": 21,
|
| 96 |
+
"r": 22,
|
| 97 |
+
"s": 23,
|
| 98 |
+
"t": 24,
|
| 99 |
+
"u": 25,
|
| 100 |
+
"v": 26,
|
| 101 |
+
"w": 27,
|
| 102 |
+
"x": 28,
|
| 103 |
+
"y": 29,
|
| 104 |
+
"z": 30,
|
| 105 |
+
"0": 31,
|
| 106 |
+
"1": 32,
|
| 107 |
+
"2": 33,
|
| 108 |
+
"3": 34,
|
| 109 |
+
"4": 35,
|
| 110 |
+
"5": 36,
|
| 111 |
+
"6": 37,
|
| 112 |
+
"7": 38,
|
| 113 |
+
"8": 39,
|
| 114 |
+
"9": 40,
|
| 115 |
+
"10": 41,
|
| 116 |
+
"11": 42,
|
| 117 |
+
"12": 43,
|
| 118 |
+
"13": 44,
|
| 119 |
+
"14": 45,
|
| 120 |
+
"15": 46,
|
| 121 |
+
"16": 47,
|
| 122 |
+
"17": 48,
|
| 123 |
+
"18": 49,
|
| 124 |
+
"19": 50,
|
| 125 |
+
"20": 51,
|
| 126 |
+
"21": 52,
|
| 127 |
+
"22": 53,
|
| 128 |
+
"23": 54,
|
| 129 |
+
"24": 55,
|
| 130 |
+
"25": 56,
|
| 131 |
+
"26": 57,
|
| 132 |
+
"27": 58,
|
| 133 |
+
"28": 59,
|
| 134 |
+
"29": 60,
|
| 135 |
+
"30": 61,
|
| 136 |
+
"31": 62,
|
| 137 |
+
"32": 63,
|
| 138 |
+
"33": 64,
|
| 139 |
+
"34": 65,
|
| 140 |
+
"35": 66,
|
| 141 |
+
"36": 67,
|
| 142 |
+
"37": 68,
|
| 143 |
+
"38": 69,
|
| 144 |
+
"39": 70,
|
| 145 |
+
"40": 71,
|
| 146 |
+
"41": 72,
|
| 147 |
+
"42": 73,
|
| 148 |
+
"43": 74,
|
| 149 |
+
"44": 75,
|
| 150 |
+
"45": 76,
|
| 151 |
+
"46": 77,
|
| 152 |
+
"47": 78,
|
| 153 |
+
"48": 79,
|
| 154 |
+
"49": 80,
|
| 155 |
+
"50": 81,
|
| 156 |
+
"51": 82,
|
| 157 |
+
"52": 83,
|
| 158 |
+
"53": 84,
|
| 159 |
+
"54": 85,
|
| 160 |
+
"55": 86,
|
| 161 |
+
"56": 87,
|
| 162 |
+
"57": 88,
|
| 163 |
+
"58": 89,
|
| 164 |
+
"59": 90,
|
| 165 |
+
"60": 91,
|
| 166 |
+
"61": 92,
|
| 167 |
+
"62": 93,
|
| 168 |
+
"63": 94,
|
| 169 |
+
"64": 95,
|
| 170 |
+
"65": 96,
|
| 171 |
+
"66": 97,
|
| 172 |
+
"67": 98,
|
| 173 |
+
"68": 99,
|
| 174 |
+
"69": 100,
|
| 175 |
+
"70": 101,
|
| 176 |
+
"71": 102,
|
| 177 |
+
"72": 103,
|
| 178 |
+
"73": 104,
|
| 179 |
+
"74": 105,
|
| 180 |
+
"75": 106,
|
| 181 |
+
"76": 107,
|
| 182 |
+
"77": 108,
|
| 183 |
+
"78": 109,
|
| 184 |
+
"79": 110,
|
| 185 |
+
"80": 111,
|
| 186 |
+
"81": 112,
|
| 187 |
+
"82": 113,
|
| 188 |
+
"83": 114,
|
| 189 |
+
"84": 115,
|
| 190 |
+
"85": 116,
|
| 191 |
+
"86": 117,
|
| 192 |
+
"87": 118,
|
| 193 |
+
"88": 119,
|
| 194 |
+
"89": 120,
|
| 195 |
+
"90": 121,
|
| 196 |
+
"91": 122,
|
| 197 |
+
"92": 123,
|
| 198 |
+
"93": 124,
|
| 199 |
+
"94": 125,
|
| 200 |
+
"95": 126,
|
| 201 |
+
"96": 127,
|
| 202 |
+
"97": 128,
|
| 203 |
+
"98": 129,
|
| 204 |
+
"99": 130,
|
| 205 |
+
"100": 131,
|
| 206 |
+
"101": 132,
|
| 207 |
+
"102": 133,
|
| 208 |
+
"103": 134,
|
| 209 |
+
"104": 135,
|
| 210 |
+
"105": 136,
|
| 211 |
+
"106": 137,
|
| 212 |
+
"107": 138,
|
| 213 |
+
"108": 139,
|
| 214 |
+
"109": 140,
|
| 215 |
+
"110": 141,
|
| 216 |
+
"111": 142,
|
| 217 |
+
"112": 143,
|
| 218 |
+
"113": 144,
|
| 219 |
+
"114": 145,
|
| 220 |
+
"115": 146,
|
| 221 |
+
"116": 147,
|
| 222 |
+
"117": 148,
|
| 223 |
+
"118": 149,
|
| 224 |
+
"119": 150,
|
| 225 |
+
"120": 151,
|
| 226 |
+
"121": 152,
|
| 227 |
+
"122": 153,
|
| 228 |
+
"123": 154,
|
| 229 |
+
"124": 155,
|
| 230 |
+
"125": 156,
|
| 231 |
+
"126": 157,
|
| 232 |
+
"127": 158,
|
| 233 |
+
"128": 159,
|
| 234 |
+
"129": 160,
|
| 235 |
+
"130": 161,
|
| 236 |
+
"131": 162,
|
| 237 |
+
"132": 163,
|
| 238 |
+
"133": 164,
|
| 239 |
+
"134": 165,
|
| 240 |
+
"135": 166,
|
| 241 |
+
"136": 167,
|
| 242 |
+
"137": 168,
|
| 243 |
+
"138": 169,
|
| 244 |
+
"139": 170,
|
| 245 |
+
"140": 171,
|
| 246 |
+
"141": 172,
|
| 247 |
+
"142": 173,
|
| 248 |
+
"143": 174,
|
| 249 |
+
"144": 175,
|
| 250 |
+
"145": 176,
|
| 251 |
+
"146": 177,
|
| 252 |
+
"147": 178,
|
| 253 |
+
"148": 179,
|
| 254 |
+
"149": 180,
|
| 255 |
+
"150": 181,
|
| 256 |
+
"151": 182,
|
| 257 |
+
"152": 183,
|
| 258 |
+
"153": 184,
|
| 259 |
+
"154": 185,
|
| 260 |
+
"155": 186,
|
| 261 |
+
"156": 187,
|
| 262 |
+
"157": 188,
|
| 263 |
+
"158": 189,
|
| 264 |
+
"159": 190,
|
| 265 |
+
"160": 191,
|
| 266 |
+
"161": 192,
|
| 267 |
+
"162": 193,
|
| 268 |
+
"163": 194,
|
| 269 |
+
"164": 195,
|
| 270 |
+
"165": 196,
|
| 271 |
+
"166": 197,
|
| 272 |
+
"167": 198,
|
| 273 |
+
"168": 199,
|
| 274 |
+
"169": 200,
|
| 275 |
+
"170": 201,
|
| 276 |
+
"171": 202,
|
| 277 |
+
"172": 203,
|
| 278 |
+
"173": 204,
|
| 279 |
+
"174": 205,
|
| 280 |
+
"175": 206,
|
| 281 |
+
"176": 207,
|
| 282 |
+
"177": 208,
|
| 283 |
+
"178": 209,
|
| 284 |
+
"179": 210,
|
| 285 |
+
"180": 211,
|
| 286 |
+
"181": 212,
|
| 287 |
+
"182": 213,
|
| 288 |
+
"183": 214,
|
| 289 |
+
"184": 215,
|
| 290 |
+
"185": 216,
|
| 291 |
+
"186": 217,
|
| 292 |
+
"187": 218,
|
| 293 |
+
"188": 219,
|
| 294 |
+
"189": 220,
|
| 295 |
+
"190": 221,
|
| 296 |
+
"191": 222,
|
| 297 |
+
"192": 223,
|
| 298 |
+
"193": 224,
|
| 299 |
+
"194": 225,
|
| 300 |
+
"195": 226,
|
| 301 |
+
"196": 227,
|
| 302 |
+
"197": 228,
|
| 303 |
+
"198": 229,
|
| 304 |
+
"199": 230,
|
| 305 |
+
"200": 231,
|
| 306 |
+
"201": 232,
|
| 307 |
+
"202": 233,
|
| 308 |
+
"203": 234,
|
| 309 |
+
"204": 235,
|
| 310 |
+
"205": 236,
|
| 311 |
+
"206": 237,
|
| 312 |
+
"207": 238,
|
| 313 |
+
"208": 239,
|
| 314 |
+
"209": 240,
|
| 315 |
+
"210": 241,
|
| 316 |
+
"211": 242,
|
| 317 |
+
"212": 243,
|
| 318 |
+
"213": 244,
|
| 319 |
+
"214": 245,
|
| 320 |
+
"215": 246,
|
| 321 |
+
"216": 247,
|
| 322 |
+
"217": 248,
|
| 323 |
+
"218": 249,
|
| 324 |
+
"219": 250,
|
| 325 |
+
"220": 251,
|
| 326 |
+
"221": 252,
|
| 327 |
+
"222": 253,
|
| 328 |
+
"223": 254,
|
| 329 |
+
"224": 255,
|
| 330 |
+
"225": 256,
|
| 331 |
+
"226": 257,
|
| 332 |
+
"227": 258,
|
| 333 |
+
"228": 259,
|
| 334 |
+
"229": 260,
|
| 335 |
+
"230": 261,
|
| 336 |
+
"231": 262,
|
| 337 |
+
"232": 263,
|
| 338 |
+
"233": 264,
|
| 339 |
+
"234": 265,
|
| 340 |
+
"235": 266,
|
| 341 |
+
"236": 267,
|
| 342 |
+
"237": 268,
|
| 343 |
+
"238": 269,
|
| 344 |
+
"239": 270,
|
| 345 |
+
"240": 271,
|
| 346 |
+
"241": 272,
|
| 347 |
+
"242": 273,
|
| 348 |
+
"243": 274,
|
| 349 |
+
"244": 275,
|
| 350 |
+
"245": 276,
|
| 351 |
+
"246": 277,
|
| 352 |
+
"247": 278,
|
| 353 |
+
"248": 279,
|
| 354 |
+
"249": 280,
|
| 355 |
+
"250": 281,
|
| 356 |
+
"251": 282,
|
| 357 |
+
"252": 283,
|
| 358 |
+
"253": 284,
|
| 359 |
+
"254": 285,
|
| 360 |
+
"255": 286,
|
| 361 |
+
"256": 287,
|
| 362 |
+
"|": 288,
|
| 363 |
+
"?": 289,
|
| 364 |
+
"(": 290,
|
| 365 |
+
")": 291
|
| 366 |
+
},
|
| 367 |
+
"unk_token": "[UNK]"
|
| 368 |
+
}
|
| 369 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "_",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[UNK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[BOS]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[EOS]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[BOS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"eos_token": "[EOS]",
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "_",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|