Upload tokenizer.json
Browse files- tokenizer.json +337 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<s>",
|
| 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": "</s>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "<unk>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "<cls>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 5,
|
| 53 |
+
"content": "<sep>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 6,
|
| 62 |
+
"content": "<mask>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"normalizer": null,
|
| 71 |
+
"pre_tokenizer": {
|
| 72 |
+
"type": "Whitespace"
|
| 73 |
+
},
|
| 74 |
+
"post_processor": null,
|
| 75 |
+
"decoder": null,
|
| 76 |
+
"model": {
|
| 77 |
+
"type": "BPE",
|
| 78 |
+
"dropout": null,
|
| 79 |
+
"unk_token": "<unk>",
|
| 80 |
+
"continuing_subword_prefix": null,
|
| 81 |
+
"end_of_word_suffix": null,
|
| 82 |
+
"fuse_unk": false,
|
| 83 |
+
"byte_fallback": false,
|
| 84 |
+
"vocab": {
|
| 85 |
+
"<s>": 0,
|
| 86 |
+
"<pad>": 1,
|
| 87 |
+
"</s>": 2,
|
| 88 |
+
"<unk>": 3,
|
| 89 |
+
"<cls>": 4,
|
| 90 |
+
"<sep>": 5,
|
| 91 |
+
"<mask>": 6,
|
| 92 |
+
"0.000": 7,
|
| 93 |
+
"0.0025": 8,
|
| 94 |
+
"-0.0025": 9,
|
| 95 |
+
"0.0050": 10,
|
| 96 |
+
"-0.0050": 11,
|
| 97 |
+
"0.0075": 12,
|
| 98 |
+
"-0.0075": 13,
|
| 99 |
+
"0.0100": 16,
|
| 100 |
+
"-0.0100": 17,
|
| 101 |
+
"0.0125": 18,
|
| 102 |
+
"-0.0125": 19,
|
| 103 |
+
"0.0150": 20,
|
| 104 |
+
"-0.0150": 21,
|
| 105 |
+
"0.0175": 22,
|
| 106 |
+
"-0.0175": 23,
|
| 107 |
+
"0.0200": 24,
|
| 108 |
+
"-0.0200": 25,
|
| 109 |
+
"0.0225": 26,
|
| 110 |
+
"-0.0225": 27,
|
| 111 |
+
"0.0250": 28,
|
| 112 |
+
"-0.0250": 29,
|
| 113 |
+
"0.0275": 30,
|
| 114 |
+
"-0.0275": 31,
|
| 115 |
+
"0.0300": 32,
|
| 116 |
+
"-0.0300": 33,
|
| 117 |
+
"0.0325": 34,
|
| 118 |
+
"-0.0325": 35,
|
| 119 |
+
"0.0350": 36,
|
| 120 |
+
"-0.0350": 37,
|
| 121 |
+
"0.0375": 38,
|
| 122 |
+
"-0.0375": 39,
|
| 123 |
+
"0.0400": 40,
|
| 124 |
+
"-0.0400": 41,
|
| 125 |
+
"0.0425": 42,
|
| 126 |
+
"-0.0425": 43,
|
| 127 |
+
"0.0450": 44,
|
| 128 |
+
"-0.0450": 45,
|
| 129 |
+
"0.0475": 46,
|
| 130 |
+
"-0.0475": 47,
|
| 131 |
+
"0.0500": 48,
|
| 132 |
+
"-0.0500": 49,
|
| 133 |
+
"0.0525": 50,
|
| 134 |
+
"-0.0525": 51,
|
| 135 |
+
"0.0550": 52,
|
| 136 |
+
"-0.0550": 53,
|
| 137 |
+
"0.0575": 54,
|
| 138 |
+
"-0.0575": 55,
|
| 139 |
+
"0.0600": 56,
|
| 140 |
+
"-0.0600": 57,
|
| 141 |
+
"0.0625": 58,
|
| 142 |
+
"-0.0625": 59,
|
| 143 |
+
"0.0650": 60,
|
| 144 |
+
"-0.0650": 61,
|
| 145 |
+
"0.0675": 62,
|
| 146 |
+
"-0.0675": 63,
|
| 147 |
+
"0.0700": 64,
|
| 148 |
+
"-0.0700": 65,
|
| 149 |
+
"0.0725": 66,
|
| 150 |
+
"-0.0725": 67,
|
| 151 |
+
"0.0750": 68,
|
| 152 |
+
"-0.0750": 69,
|
| 153 |
+
"0.0775": 70,
|
| 154 |
+
"-0.0775": 71,
|
| 155 |
+
"0.0800": 72,
|
| 156 |
+
"-0.0800": 73,
|
| 157 |
+
"0.0825": 74,
|
| 158 |
+
"-0.0825": 75,
|
| 159 |
+
"0.0850": 76,
|
| 160 |
+
"-0.0850": 77,
|
| 161 |
+
"0.0875": 78,
|
| 162 |
+
"-0.0875": 79,
|
| 163 |
+
"0.0900": 80,
|
| 164 |
+
"-0.0900": 81,
|
| 165 |
+
"0.0925": 82,
|
| 166 |
+
"-0.0925": 83,
|
| 167 |
+
"0.0950": 84,
|
| 168 |
+
"-0.0950": 85,
|
| 169 |
+
"0.0975": 86,
|
| 170 |
+
"-0.0975": 87,
|
| 171 |
+
"0.1000": 88,
|
| 172 |
+
"-0.1000": 89,
|
| 173 |
+
"0.1025": 90,
|
| 174 |
+
"-0.1025": 91,
|
| 175 |
+
"0.1050": 92,
|
| 176 |
+
"-0.1050": 93,
|
| 177 |
+
"0.1075": 94,
|
| 178 |
+
"-0.1075": 95,
|
| 179 |
+
"0.1100": 96,
|
| 180 |
+
"-0.1100": 97,
|
| 181 |
+
"0.1125": 98,
|
| 182 |
+
"-0.1125": 99,
|
| 183 |
+
"0.1150": 100,
|
| 184 |
+
"-0.1150": 101,
|
| 185 |
+
"0.1175": 102,
|
| 186 |
+
"-0.1175": 103,
|
| 187 |
+
"0.1200": 104,
|
| 188 |
+
"-0.1200": 105,
|
| 189 |
+
"0.1225": 106,
|
| 190 |
+
"-0.1225": 107,
|
| 191 |
+
"0.1250": 108,
|
| 192 |
+
"-0.1250": 109,
|
| 193 |
+
"0.1275": 110,
|
| 194 |
+
"-0.1275": 111,
|
| 195 |
+
"0.1300": 112,
|
| 196 |
+
"-0.1300": 113,
|
| 197 |
+
"0.1325": 114,
|
| 198 |
+
"-0.1325": 115,
|
| 199 |
+
"0.1350": 116,
|
| 200 |
+
"-0.1350": 117,
|
| 201 |
+
"0.1375": 118,
|
| 202 |
+
"-0.1375": 119,
|
| 203 |
+
"0.1400": 120,
|
| 204 |
+
"-0.1400": 121,
|
| 205 |
+
"0.1425": 122,
|
| 206 |
+
"-0.1425": 123,
|
| 207 |
+
"0.1450": 124,
|
| 208 |
+
"-0.1450": 125,
|
| 209 |
+
"0.1475": 126,
|
| 210 |
+
"-0.1475": 127,
|
| 211 |
+
"0.1500": 128,
|
| 212 |
+
"-0.1500": 129,
|
| 213 |
+
"0.1525": 130,
|
| 214 |
+
"-0.1525": 131,
|
| 215 |
+
"0.1550": 132,
|
| 216 |
+
"-0.1550": 133,
|
| 217 |
+
"0.1575": 134,
|
| 218 |
+
"-0.1575": 135,
|
| 219 |
+
"0.1600": 136,
|
| 220 |
+
"-0.1600": 137,
|
| 221 |
+
"0.1625": 138,
|
| 222 |
+
"-0.1625": 139,
|
| 223 |
+
"0.1650": 140,
|
| 224 |
+
"-0.1650": 141,
|
| 225 |
+
"0.1675": 142,
|
| 226 |
+
"-0.1675": 143,
|
| 227 |
+
"0.1700": 144,
|
| 228 |
+
"-0.1700": 145,
|
| 229 |
+
"0.1725": 146,
|
| 230 |
+
"-0.1725": 147,
|
| 231 |
+
"0.1750": 148,
|
| 232 |
+
"-0.1750": 149,
|
| 233 |
+
"0.1775": 150,
|
| 234 |
+
"-0.1775": 151,
|
| 235 |
+
"0.1800": 152,
|
| 236 |
+
"-0.1800": 153,
|
| 237 |
+
"0.1825": 154,
|
| 238 |
+
"-0.1825": 155,
|
| 239 |
+
"0.1850": 156,
|
| 240 |
+
"-0.1850": 157,
|
| 241 |
+
"0.1875": 158,
|
| 242 |
+
"-0.1875": 159,
|
| 243 |
+
"0.1900": 160,
|
| 244 |
+
"-0.1900": 161,
|
| 245 |
+
"0.1925": 162,
|
| 246 |
+
"-0.1925": 163,
|
| 247 |
+
"0.1950": 164,
|
| 248 |
+
"-0.1950": 165,
|
| 249 |
+
"0.1975": 166,
|
| 250 |
+
"-0.1975": 167,
|
| 251 |
+
"0.2000": 168,
|
| 252 |
+
"-0.2000": 169,
|
| 253 |
+
"0.2025": 170,
|
| 254 |
+
"-0.2025": 171,
|
| 255 |
+
"0.2050": 172,
|
| 256 |
+
"-0.2050": 173,
|
| 257 |
+
"0.2075": 174,
|
| 258 |
+
"-0.2075": 175,
|
| 259 |
+
"0.2100": 176,
|
| 260 |
+
"-0.2100": 177,
|
| 261 |
+
"0.2125": 178,
|
| 262 |
+
"-0.2125": 179,
|
| 263 |
+
"0.2150": 180,
|
| 264 |
+
"-0.2150": 181,
|
| 265 |
+
"0.2175": 182,
|
| 266 |
+
"-0.2175": 183,
|
| 267 |
+
"0.2200": 184,
|
| 268 |
+
"-0.2200": 185,
|
| 269 |
+
"0.2225": 186,
|
| 270 |
+
"-0.2225": 187,
|
| 271 |
+
"0.2250": 188,
|
| 272 |
+
"-0.2250": 189,
|
| 273 |
+
"0.2275": 190,
|
| 274 |
+
"-0.2275": 191,
|
| 275 |
+
"0.2300": 192,
|
| 276 |
+
"-0.2300": 193,
|
| 277 |
+
"0.2325": 194,
|
| 278 |
+
"-0.2325": 195,
|
| 279 |
+
"0.2350": 196,
|
| 280 |
+
"-0.2350": 197,
|
| 281 |
+
"0.2375": 198,
|
| 282 |
+
"-0.2375": 199,
|
| 283 |
+
"0.2400": 200,
|
| 284 |
+
"-0.2400": 201,
|
| 285 |
+
"0.2425": 202,
|
| 286 |
+
"-0.2425": 203,
|
| 287 |
+
"0.2450": 204,
|
| 288 |
+
"-0.2450": 205,
|
| 289 |
+
"0.2475": 206,
|
| 290 |
+
"-0.2475": 207,
|
| 291 |
+
"0.2500": 208,
|
| 292 |
+
"-0.2500": 209,
|
| 293 |
+
"0.2525": 210,
|
| 294 |
+
"-0.2525": 211,
|
| 295 |
+
"0.2550": 212,
|
| 296 |
+
"-0.2550": 213,
|
| 297 |
+
"0.2575": 214,
|
| 298 |
+
"-0.2575": 215,
|
| 299 |
+
"0.2600": 216,
|
| 300 |
+
"-0.2600": 217,
|
| 301 |
+
"0.2625": 218,
|
| 302 |
+
"-0.2625": 219,
|
| 303 |
+
"0.2650": 220,
|
| 304 |
+
"-0.2650": 221,
|
| 305 |
+
"0.2675": 222,
|
| 306 |
+
"-0.2675": 223,
|
| 307 |
+
"0.2700": 224,
|
| 308 |
+
"-0.2700": 225,
|
| 309 |
+
"0.2725": 226,
|
| 310 |
+
"-0.2725": 227,
|
| 311 |
+
"0.2750": 228,
|
| 312 |
+
"-0.2750": 229,
|
| 313 |
+
"0.2775": 230,
|
| 314 |
+
"-0.2775": 231,
|
| 315 |
+
"0.2800": 232,
|
| 316 |
+
"-0.2800": 233,
|
| 317 |
+
"0.2825": 234,
|
| 318 |
+
"-0.2825": 235,
|
| 319 |
+
"0.2850": 236,
|
| 320 |
+
"-0.2850": 237,
|
| 321 |
+
"0.2875": 238,
|
| 322 |
+
"-0.2875": 239,
|
| 323 |
+
"0.2900": 240,
|
| 324 |
+
"-0.2900": 241,
|
| 325 |
+
"0.2925": 242,
|
| 326 |
+
"-0.2925": 243,
|
| 327 |
+
"0.2950": 244,
|
| 328 |
+
"-0.2950": 245,
|
| 329 |
+
"0.2975": 246,
|
| 330 |
+
"-0.2975": 247,
|
| 331 |
+
"0.3000": 248
|
| 332 |
+
},
|
| 333 |
+
"merges": [
|
| 334 |
+
|
| 335 |
+
]
|
| 336 |
+
}
|
| 337 |
+
}
|