Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer.json +539 -0
- tokenizer_config.json +25 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "[PAD]",
|
| 3 |
+
"unk_token": "[UNK]"
|
| 4 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,539 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 500,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 501,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"normalizer": null,
|
| 26 |
+
"pre_tokenizer": {
|
| 27 |
+
"type": "WhitespaceSplit"
|
| 28 |
+
},
|
| 29 |
+
"post_processor": null,
|
| 30 |
+
"decoder": null,
|
| 31 |
+
"model": {
|
| 32 |
+
"type": "WordLevel",
|
| 33 |
+
"vocab": {
|
| 34 |
+
"<1": 0,
|
| 35 |
+
"1>": 1,
|
| 36 |
+
"<2": 2,
|
| 37 |
+
"2>": 3,
|
| 38 |
+
"<3": 4,
|
| 39 |
+
"3>": 5,
|
| 40 |
+
"<4": 6,
|
| 41 |
+
"4>": 7,
|
| 42 |
+
"<5": 8,
|
| 43 |
+
"5>": 9,
|
| 44 |
+
"<6": 10,
|
| 45 |
+
"6>": 11,
|
| 46 |
+
"<7": 12,
|
| 47 |
+
"7>": 13,
|
| 48 |
+
"<8": 14,
|
| 49 |
+
"8>": 15,
|
| 50 |
+
"<9": 16,
|
| 51 |
+
"9>": 17,
|
| 52 |
+
"<10": 18,
|
| 53 |
+
"10>": 19,
|
| 54 |
+
"<11": 20,
|
| 55 |
+
"11>": 21,
|
| 56 |
+
"<12": 22,
|
| 57 |
+
"12>": 23,
|
| 58 |
+
"<13": 24,
|
| 59 |
+
"13>": 25,
|
| 60 |
+
"<14": 26,
|
| 61 |
+
"14>": 27,
|
| 62 |
+
"<15": 28,
|
| 63 |
+
"15>": 29,
|
| 64 |
+
"<16": 30,
|
| 65 |
+
"16>": 31,
|
| 66 |
+
"<17": 32,
|
| 67 |
+
"17>": 33,
|
| 68 |
+
"<18": 34,
|
| 69 |
+
"18>": 35,
|
| 70 |
+
"<19": 36,
|
| 71 |
+
"19>": 37,
|
| 72 |
+
"<20": 38,
|
| 73 |
+
"20>": 39,
|
| 74 |
+
"<21": 40,
|
| 75 |
+
"21>": 41,
|
| 76 |
+
"<22": 42,
|
| 77 |
+
"22>": 43,
|
| 78 |
+
"<23": 44,
|
| 79 |
+
"23>": 45,
|
| 80 |
+
"<24": 46,
|
| 81 |
+
"24>": 47,
|
| 82 |
+
"<25": 48,
|
| 83 |
+
"25>": 49,
|
| 84 |
+
"<26": 50,
|
| 85 |
+
"26>": 51,
|
| 86 |
+
"<27": 52,
|
| 87 |
+
"27>": 53,
|
| 88 |
+
"<28": 54,
|
| 89 |
+
"28>": 55,
|
| 90 |
+
"<29": 56,
|
| 91 |
+
"29>": 57,
|
| 92 |
+
"<30": 58,
|
| 93 |
+
"30>": 59,
|
| 94 |
+
"<31": 60,
|
| 95 |
+
"31>": 61,
|
| 96 |
+
"<32": 62,
|
| 97 |
+
"32>": 63,
|
| 98 |
+
"<33": 64,
|
| 99 |
+
"33>": 65,
|
| 100 |
+
"<34": 66,
|
| 101 |
+
"34>": 67,
|
| 102 |
+
"<35": 68,
|
| 103 |
+
"35>": 69,
|
| 104 |
+
"<36": 70,
|
| 105 |
+
"36>": 71,
|
| 106 |
+
"<37": 72,
|
| 107 |
+
"37>": 73,
|
| 108 |
+
"<38": 74,
|
| 109 |
+
"38>": 75,
|
| 110 |
+
"<39": 76,
|
| 111 |
+
"39>": 77,
|
| 112 |
+
"<40": 78,
|
| 113 |
+
"40>": 79,
|
| 114 |
+
"<41": 80,
|
| 115 |
+
"41>": 81,
|
| 116 |
+
"<42": 82,
|
| 117 |
+
"42>": 83,
|
| 118 |
+
"<43": 84,
|
| 119 |
+
"43>": 85,
|
| 120 |
+
"<44": 86,
|
| 121 |
+
"44>": 87,
|
| 122 |
+
"<45": 88,
|
| 123 |
+
"45>": 89,
|
| 124 |
+
"<46": 90,
|
| 125 |
+
"46>": 91,
|
| 126 |
+
"<47": 92,
|
| 127 |
+
"47>": 93,
|
| 128 |
+
"<48": 94,
|
| 129 |
+
"48>": 95,
|
| 130 |
+
"<49": 96,
|
| 131 |
+
"49>": 97,
|
| 132 |
+
"<50": 98,
|
| 133 |
+
"50>": 99,
|
| 134 |
+
"<51": 100,
|
| 135 |
+
"51>": 101,
|
| 136 |
+
"<52": 102,
|
| 137 |
+
"52>": 103,
|
| 138 |
+
"<53": 104,
|
| 139 |
+
"53>": 105,
|
| 140 |
+
"<54": 106,
|
| 141 |
+
"54>": 107,
|
| 142 |
+
"<55": 108,
|
| 143 |
+
"55>": 109,
|
| 144 |
+
"<56": 110,
|
| 145 |
+
"56>": 111,
|
| 146 |
+
"<57": 112,
|
| 147 |
+
"57>": 113,
|
| 148 |
+
"<58": 114,
|
| 149 |
+
"58>": 115,
|
| 150 |
+
"<59": 116,
|
| 151 |
+
"59>": 117,
|
| 152 |
+
"<60": 118,
|
| 153 |
+
"60>": 119,
|
| 154 |
+
"<61": 120,
|
| 155 |
+
"61>": 121,
|
| 156 |
+
"<62": 122,
|
| 157 |
+
"62>": 123,
|
| 158 |
+
"<63": 124,
|
| 159 |
+
"63>": 125,
|
| 160 |
+
"<64": 126,
|
| 161 |
+
"64>": 127,
|
| 162 |
+
"<65": 128,
|
| 163 |
+
"65>": 129,
|
| 164 |
+
"<66": 130,
|
| 165 |
+
"66>": 131,
|
| 166 |
+
"<67": 132,
|
| 167 |
+
"67>": 133,
|
| 168 |
+
"<68": 134,
|
| 169 |
+
"68>": 135,
|
| 170 |
+
"<69": 136,
|
| 171 |
+
"69>": 137,
|
| 172 |
+
"<70": 138,
|
| 173 |
+
"70>": 139,
|
| 174 |
+
"<71": 140,
|
| 175 |
+
"71>": 141,
|
| 176 |
+
"<72": 142,
|
| 177 |
+
"72>": 143,
|
| 178 |
+
"<73": 144,
|
| 179 |
+
"73>": 145,
|
| 180 |
+
"<74": 146,
|
| 181 |
+
"74>": 147,
|
| 182 |
+
"<75": 148,
|
| 183 |
+
"75>": 149,
|
| 184 |
+
"<76": 150,
|
| 185 |
+
"76>": 151,
|
| 186 |
+
"<77": 152,
|
| 187 |
+
"77>": 153,
|
| 188 |
+
"<78": 154,
|
| 189 |
+
"78>": 155,
|
| 190 |
+
"<79": 156,
|
| 191 |
+
"79>": 157,
|
| 192 |
+
"<80": 158,
|
| 193 |
+
"80>": 159,
|
| 194 |
+
"<81": 160,
|
| 195 |
+
"81>": 161,
|
| 196 |
+
"<82": 162,
|
| 197 |
+
"82>": 163,
|
| 198 |
+
"<83": 164,
|
| 199 |
+
"83>": 165,
|
| 200 |
+
"<84": 166,
|
| 201 |
+
"84>": 167,
|
| 202 |
+
"<85": 168,
|
| 203 |
+
"85>": 169,
|
| 204 |
+
"<86": 170,
|
| 205 |
+
"86>": 171,
|
| 206 |
+
"<87": 172,
|
| 207 |
+
"87>": 173,
|
| 208 |
+
"<88": 174,
|
| 209 |
+
"88>": 175,
|
| 210 |
+
"<89": 176,
|
| 211 |
+
"89>": 177,
|
| 212 |
+
"<90": 178,
|
| 213 |
+
"90>": 179,
|
| 214 |
+
"<91": 180,
|
| 215 |
+
"91>": 181,
|
| 216 |
+
"<92": 182,
|
| 217 |
+
"92>": 183,
|
| 218 |
+
"<93": 184,
|
| 219 |
+
"93>": 185,
|
| 220 |
+
"<94": 186,
|
| 221 |
+
"94>": 187,
|
| 222 |
+
"<95": 188,
|
| 223 |
+
"95>": 189,
|
| 224 |
+
"<96": 190,
|
| 225 |
+
"96>": 191,
|
| 226 |
+
"<97": 192,
|
| 227 |
+
"97>": 193,
|
| 228 |
+
"<98": 194,
|
| 229 |
+
"98>": 195,
|
| 230 |
+
"<99": 196,
|
| 231 |
+
"99>": 197,
|
| 232 |
+
"<100": 198,
|
| 233 |
+
"100>": 199,
|
| 234 |
+
"<101": 200,
|
| 235 |
+
"101>": 201,
|
| 236 |
+
"<102": 202,
|
| 237 |
+
"102>": 203,
|
| 238 |
+
"<103": 204,
|
| 239 |
+
"103>": 205,
|
| 240 |
+
"<104": 206,
|
| 241 |
+
"104>": 207,
|
| 242 |
+
"<105": 208,
|
| 243 |
+
"105>": 209,
|
| 244 |
+
"<106": 210,
|
| 245 |
+
"106>": 211,
|
| 246 |
+
"<107": 212,
|
| 247 |
+
"107>": 213,
|
| 248 |
+
"<108": 214,
|
| 249 |
+
"108>": 215,
|
| 250 |
+
"<109": 216,
|
| 251 |
+
"109>": 217,
|
| 252 |
+
"<110": 218,
|
| 253 |
+
"110>": 219,
|
| 254 |
+
"<111": 220,
|
| 255 |
+
"111>": 221,
|
| 256 |
+
"<112": 222,
|
| 257 |
+
"112>": 223,
|
| 258 |
+
"<113": 224,
|
| 259 |
+
"113>": 225,
|
| 260 |
+
"<114": 226,
|
| 261 |
+
"114>": 227,
|
| 262 |
+
"<115": 228,
|
| 263 |
+
"115>": 229,
|
| 264 |
+
"<116": 230,
|
| 265 |
+
"116>": 231,
|
| 266 |
+
"<117": 232,
|
| 267 |
+
"117>": 233,
|
| 268 |
+
"<118": 234,
|
| 269 |
+
"118>": 235,
|
| 270 |
+
"<119": 236,
|
| 271 |
+
"119>": 237,
|
| 272 |
+
"<120": 238,
|
| 273 |
+
"120>": 239,
|
| 274 |
+
"<121": 240,
|
| 275 |
+
"121>": 241,
|
| 276 |
+
"<122": 242,
|
| 277 |
+
"122>": 243,
|
| 278 |
+
"<123": 244,
|
| 279 |
+
"123>": 245,
|
| 280 |
+
"<124": 246,
|
| 281 |
+
"124>": 247,
|
| 282 |
+
"<125": 248,
|
| 283 |
+
"125>": 249,
|
| 284 |
+
"<126": 250,
|
| 285 |
+
"126>": 251,
|
| 286 |
+
"<127": 252,
|
| 287 |
+
"127>": 253,
|
| 288 |
+
"<128": 254,
|
| 289 |
+
"128>": 255,
|
| 290 |
+
"<129": 256,
|
| 291 |
+
"129>": 257,
|
| 292 |
+
"<130": 258,
|
| 293 |
+
"130>": 259,
|
| 294 |
+
"<131": 260,
|
| 295 |
+
"131>": 261,
|
| 296 |
+
"<132": 262,
|
| 297 |
+
"132>": 263,
|
| 298 |
+
"<133": 264,
|
| 299 |
+
"133>": 265,
|
| 300 |
+
"<134": 266,
|
| 301 |
+
"134>": 267,
|
| 302 |
+
"<135": 268,
|
| 303 |
+
"135>": 269,
|
| 304 |
+
"<136": 270,
|
| 305 |
+
"136>": 271,
|
| 306 |
+
"<137": 272,
|
| 307 |
+
"137>": 273,
|
| 308 |
+
"<138": 274,
|
| 309 |
+
"138>": 275,
|
| 310 |
+
"<139": 276,
|
| 311 |
+
"139>": 277,
|
| 312 |
+
"<140": 278,
|
| 313 |
+
"140>": 279,
|
| 314 |
+
"<141": 280,
|
| 315 |
+
"141>": 281,
|
| 316 |
+
"<142": 282,
|
| 317 |
+
"142>": 283,
|
| 318 |
+
"<143": 284,
|
| 319 |
+
"143>": 285,
|
| 320 |
+
"<144": 286,
|
| 321 |
+
"144>": 287,
|
| 322 |
+
"<145": 288,
|
| 323 |
+
"145>": 289,
|
| 324 |
+
"<146": 290,
|
| 325 |
+
"146>": 291,
|
| 326 |
+
"<147": 292,
|
| 327 |
+
"147>": 293,
|
| 328 |
+
"<148": 294,
|
| 329 |
+
"148>": 295,
|
| 330 |
+
"<149": 296,
|
| 331 |
+
"149>": 297,
|
| 332 |
+
"<150": 298,
|
| 333 |
+
"150>": 299,
|
| 334 |
+
"<151": 300,
|
| 335 |
+
"151>": 301,
|
| 336 |
+
"<152": 302,
|
| 337 |
+
"152>": 303,
|
| 338 |
+
"<153": 304,
|
| 339 |
+
"153>": 305,
|
| 340 |
+
"<154": 306,
|
| 341 |
+
"154>": 307,
|
| 342 |
+
"<155": 308,
|
| 343 |
+
"155>": 309,
|
| 344 |
+
"<156": 310,
|
| 345 |
+
"156>": 311,
|
| 346 |
+
"<157": 312,
|
| 347 |
+
"157>": 313,
|
| 348 |
+
"<158": 314,
|
| 349 |
+
"158>": 315,
|
| 350 |
+
"<159": 316,
|
| 351 |
+
"159>": 317,
|
| 352 |
+
"<160": 318,
|
| 353 |
+
"160>": 319,
|
| 354 |
+
"<161": 320,
|
| 355 |
+
"161>": 321,
|
| 356 |
+
"<162": 322,
|
| 357 |
+
"162>": 323,
|
| 358 |
+
"<163": 324,
|
| 359 |
+
"163>": 325,
|
| 360 |
+
"<164": 326,
|
| 361 |
+
"164>": 327,
|
| 362 |
+
"<165": 328,
|
| 363 |
+
"165>": 329,
|
| 364 |
+
"<166": 330,
|
| 365 |
+
"166>": 331,
|
| 366 |
+
"<167": 332,
|
| 367 |
+
"167>": 333,
|
| 368 |
+
"<168": 334,
|
| 369 |
+
"168>": 335,
|
| 370 |
+
"<169": 336,
|
| 371 |
+
"169>": 337,
|
| 372 |
+
"<170": 338,
|
| 373 |
+
"170>": 339,
|
| 374 |
+
"<171": 340,
|
| 375 |
+
"171>": 341,
|
| 376 |
+
"<172": 342,
|
| 377 |
+
"172>": 343,
|
| 378 |
+
"<173": 344,
|
| 379 |
+
"173>": 345,
|
| 380 |
+
"<174": 346,
|
| 381 |
+
"174>": 347,
|
| 382 |
+
"<175": 348,
|
| 383 |
+
"175>": 349,
|
| 384 |
+
"<176": 350,
|
| 385 |
+
"176>": 351,
|
| 386 |
+
"<177": 352,
|
| 387 |
+
"177>": 353,
|
| 388 |
+
"<178": 354,
|
| 389 |
+
"178>": 355,
|
| 390 |
+
"<179": 356,
|
| 391 |
+
"179>": 357,
|
| 392 |
+
"<180": 358,
|
| 393 |
+
"180>": 359,
|
| 394 |
+
"<181": 360,
|
| 395 |
+
"181>": 361,
|
| 396 |
+
"<182": 362,
|
| 397 |
+
"182>": 363,
|
| 398 |
+
"<183": 364,
|
| 399 |
+
"183>": 365,
|
| 400 |
+
"<184": 366,
|
| 401 |
+
"184>": 367,
|
| 402 |
+
"<185": 368,
|
| 403 |
+
"185>": 369,
|
| 404 |
+
"<186": 370,
|
| 405 |
+
"186>": 371,
|
| 406 |
+
"<187": 372,
|
| 407 |
+
"187>": 373,
|
| 408 |
+
"<188": 374,
|
| 409 |
+
"188>": 375,
|
| 410 |
+
"<189": 376,
|
| 411 |
+
"189>": 377,
|
| 412 |
+
"<190": 378,
|
| 413 |
+
"190>": 379,
|
| 414 |
+
"<191": 380,
|
| 415 |
+
"191>": 381,
|
| 416 |
+
"<192": 382,
|
| 417 |
+
"192>": 383,
|
| 418 |
+
"<193": 384,
|
| 419 |
+
"193>": 385,
|
| 420 |
+
"<194": 386,
|
| 421 |
+
"194>": 387,
|
| 422 |
+
"<195": 388,
|
| 423 |
+
"195>": 389,
|
| 424 |
+
"<196": 390,
|
| 425 |
+
"196>": 391,
|
| 426 |
+
"<197": 392,
|
| 427 |
+
"197>": 393,
|
| 428 |
+
"<198": 394,
|
| 429 |
+
"198>": 395,
|
| 430 |
+
"<199": 396,
|
| 431 |
+
"199>": 397,
|
| 432 |
+
"<200": 398,
|
| 433 |
+
"200>": 399,
|
| 434 |
+
"<201": 400,
|
| 435 |
+
"201>": 401,
|
| 436 |
+
"<202": 402,
|
| 437 |
+
"202>": 403,
|
| 438 |
+
"<203": 404,
|
| 439 |
+
"203>": 405,
|
| 440 |
+
"<204": 406,
|
| 441 |
+
"204>": 407,
|
| 442 |
+
"<205": 408,
|
| 443 |
+
"205>": 409,
|
| 444 |
+
"<206": 410,
|
| 445 |
+
"206>": 411,
|
| 446 |
+
"<207": 412,
|
| 447 |
+
"207>": 413,
|
| 448 |
+
"<208": 414,
|
| 449 |
+
"208>": 415,
|
| 450 |
+
"<209": 416,
|
| 451 |
+
"209>": 417,
|
| 452 |
+
"<210": 418,
|
| 453 |
+
"210>": 419,
|
| 454 |
+
"<211": 420,
|
| 455 |
+
"211>": 421,
|
| 456 |
+
"<212": 422,
|
| 457 |
+
"212>": 423,
|
| 458 |
+
"<213": 424,
|
| 459 |
+
"213>": 425,
|
| 460 |
+
"<214": 426,
|
| 461 |
+
"214>": 427,
|
| 462 |
+
"<215": 428,
|
| 463 |
+
"215>": 429,
|
| 464 |
+
"<216": 430,
|
| 465 |
+
"216>": 431,
|
| 466 |
+
"<217": 432,
|
| 467 |
+
"217>": 433,
|
| 468 |
+
"<218": 434,
|
| 469 |
+
"218>": 435,
|
| 470 |
+
"<219": 436,
|
| 471 |
+
"219>": 437,
|
| 472 |
+
"<220": 438,
|
| 473 |
+
"220>": 439,
|
| 474 |
+
"<221": 440,
|
| 475 |
+
"221>": 441,
|
| 476 |
+
"<222": 442,
|
| 477 |
+
"222>": 443,
|
| 478 |
+
"<223": 444,
|
| 479 |
+
"223>": 445,
|
| 480 |
+
"<224": 446,
|
| 481 |
+
"224>": 447,
|
| 482 |
+
"<225": 448,
|
| 483 |
+
"225>": 449,
|
| 484 |
+
"<226": 450,
|
| 485 |
+
"226>": 451,
|
| 486 |
+
"<227": 452,
|
| 487 |
+
"227>": 453,
|
| 488 |
+
"<228": 454,
|
| 489 |
+
"228>": 455,
|
| 490 |
+
"<229": 456,
|
| 491 |
+
"229>": 457,
|
| 492 |
+
"<230": 458,
|
| 493 |
+
"230>": 459,
|
| 494 |
+
"<231": 460,
|
| 495 |
+
"231>": 461,
|
| 496 |
+
"<232": 462,
|
| 497 |
+
"232>": 463,
|
| 498 |
+
"<233": 464,
|
| 499 |
+
"233>": 465,
|
| 500 |
+
"<234": 466,
|
| 501 |
+
"234>": 467,
|
| 502 |
+
"<235": 468,
|
| 503 |
+
"235>": 469,
|
| 504 |
+
"<236": 470,
|
| 505 |
+
"236>": 471,
|
| 506 |
+
"<237": 472,
|
| 507 |
+
"237>": 473,
|
| 508 |
+
"<238": 474,
|
| 509 |
+
"238>": 475,
|
| 510 |
+
"<239": 476,
|
| 511 |
+
"239>": 477,
|
| 512 |
+
"<240": 478,
|
| 513 |
+
"240>": 479,
|
| 514 |
+
"<241": 480,
|
| 515 |
+
"241>": 481,
|
| 516 |
+
"<242": 482,
|
| 517 |
+
"242>": 483,
|
| 518 |
+
"<243": 484,
|
| 519 |
+
"243>": 485,
|
| 520 |
+
"<244": 486,
|
| 521 |
+
"244>": 487,
|
| 522 |
+
"<245": 488,
|
| 523 |
+
"245>": 489,
|
| 524 |
+
"<246": 490,
|
| 525 |
+
"246>": 491,
|
| 526 |
+
"<247": 492,
|
| 527 |
+
"247>": 493,
|
| 528 |
+
"<248": 494,
|
| 529 |
+
"248>": 495,
|
| 530 |
+
"<249": 496,
|
| 531 |
+
"249>": 497,
|
| 532 |
+
"<250": 498,
|
| 533 |
+
"250>": 499,
|
| 534 |
+
"[UNK]": 500,
|
| 535 |
+
"[PAD]": 501
|
| 536 |
+
},
|
| 537 |
+
"unk_token": "[UNK]"
|
| 538 |
+
}
|
| 539 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"500": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"501": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
+
"clean_up_tokenization_spaces": true,
|
| 21 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": "[PAD]",
|
| 23 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 24 |
+
"unk_token": "[UNK]"
|
| 25 |
+
}
|