ByteDance/Dolphin
519701
1{2 "added_tokens_decoder": {3 "0": {4 "content": "<s>",5 "lstrip": false,6 "normalized": false,7 "rstrip": false,8 "single_word": false,9 "special": true10 },11 "1": {12 "content": "<pad>",13 "lstrip": false,14 "normalized": false,15 "rstrip": false,16 "single_word": false,17 "special": true18 },19 "2": {20 "content": "</s>",21 "lstrip": false,22 "normalized": false,23 "rstrip": false,24 "single_word": false,25 "special": true26 },27 "3": {28 "content": "<unk>",29 "lstrip": false,30 "normalized": false,31 "rstrip": false,32 "single_word": false,33 "special": true34 },35 "4": {36 "content": "[START_REF]",37 "lstrip": false,38 "normalized": false,39 "rstrip": false,40 "single_word": false,41 "special": true42 },43 "5": {44 "content": "[END_REF]",45 "lstrip": false,46 "normalized": false,47 "rstrip": false,48 "single_word": false,49 "special": true50 },51 "6": {52 "content": "[IMAGE]",53 "lstrip": false,54 "normalized": false,55 "rstrip": false,56 "single_word": false,57 "special": true58 },59 "7": {60 "content": "<fragments>",61 "lstrip": false,62 "normalized": false,63 "rstrip": false,64 "single_word": false,65 "special": true66 },67 "8": {68 "content": "</fragments>",69 "lstrip": false,70 "normalized": false,71 "rstrip": false,72 "single_word": false,73 "special": true74 },75 "9": {76 "content": "<work>",77 "lstrip": false,78 "normalized": false,79 "rstrip": false,80 "single_word": false,81 "special": true82 },83 "10": {84 "content": "</work>",85 "lstrip": false,86 "normalized": false,87 "rstrip": false,88 "single_word": false,89 "special": true90 },91 "11": {92 "content": "[START_SUP]",93 "lstrip": false,94 "normalized": false,95 "rstrip": false,96 "single_word": false,97 "special": true98 },99 "12": {100 "content": "[END_SUP]",101 "lstrip": false,102 "normalized": false,103 "rstrip": false,104 "single_word": false,105 "special": true106 },107 "13": {108 "content": "[START_SUB]",109 "lstrip": false,110 "normalized": false,111 "rstrip": false,112 "single_word": false,113 "special": true114 },115 "14": {116 "content": "[END_SUB]",117 "lstrip": false,118 "normalized": false,119 "rstrip": false,120 "single_word": false,121 "special": true122 },123 "15": {124 "content": "[START_DNA]",125 "lstrip": false,126 "normalized": false,127 "rstrip": false,128 "single_word": false,129 "special": true130 },131 "16": {132 "content": "[END_DNA]",133 "lstrip": false,134 "normalized": false,135 "rstrip": false,136 "single_word": false,137 "special": true138 },139 "17": {140 "content": "[START_AMINO]",141 "lstrip": false,142 "normalized": false,143 "rstrip": false,144 "single_word": false,145 "special": true146 },147 "18": {148 "content": "[END_AMINO]",149 "lstrip": false,150 "normalized": false,151 "rstrip": false,152 "single_word": false,153 "special": true154 },155 "19": {156 "content": "[START_SMILES]",157 "lstrip": false,158 "normalized": false,159 "rstrip": false,160 "single_word": false,161 "special": true162 },163 "20": {164 "content": "[END_SMILES]",165 "lstrip": false,166 "normalized": false,167 "rstrip": false,168 "single_word": false,169 "special": true170 },171 "21": {172 "content": "[START_I_SMILES]",173 "lstrip": false,174 "normalized": false,175 "rstrip": false,176 "single_word": false,177 "special": true178 },179 "22": {180 "content": "[END_I_SMILES]",181 "lstrip": false,182 "normalized": false,183 "rstrip": false,184 "single_word": false,185 "special": true186 },187 "50000": {188 "content": "ㆀ",189 "lstrip": false,190 "normalized": false,191 "rstrip": false,192 "single_word": false,193 "special": true194 },195 "50001": {196 "content": "쓚",197 "lstrip": false,198 "normalized": false,199 "rstrip": false,200 "single_word": false,201 "special": true202 },203 "50002": {204 "content": "뵞",205 "lstrip": false,206 "normalized": false,207 "rstrip": false,208 "single_word": false,209 "special": true210 },211 "50003": {212 "content": "뾥",213 "lstrip": false,214 "normalized": false,215 "rstrip": false,216 "single_word": false,217 "special": true218 },219 "50004": {220 "content": "빸",221 "lstrip": false,222 "normalized": false,223 "rstrip": false,224 "single_word": false,225 "special": true226 },227 "50005": {228 "content": "踪",229 "lstrip": false,230 "normalized": false,231 "rstrip": false,232 "single_word": false,233 "special": true234 },235 "50006": {236 "content": "聾",237 "lstrip": false,238 "normalized": false,239 "rstrip": false,240 "single_word": false,241 "special": true242 },243 "50007": {244 "content": "摭",245 "lstrip": false,246 "normalized": false,247 "rstrip": false,248 "single_word": false,249 "special": true250 },251 "50008": {252 "content": "哔",253 "lstrip": false,254 "normalized": false,255 "rstrip": false,256 "single_word": false,257 "special": true258 },259 "50009": {260 "content": "蠼",261 "lstrip": false,262 "normalized": false,263 "rstrip": false,264 "single_word": false,265 "special": true266 },267 "50010": {268 "content": "涛",269 "lstrip": false,270 "normalized": false,271 "rstrip": false,272 "single_word": false,273 "special": true274 },275 "50011": {276 "content": "瞥",277 "lstrip": false,278 "normalized": false,279 "rstrip": false,280 "single_word": false,281 "special": true282 },283 "50012": {284 "content": "戗",285 "lstrip": false,286 "normalized": false,287 "rstrip": false,288 "single_word": false,289 "special": true290 },291 "50013": {292 "content": "骑",293 "lstrip": false,294 "normalized": false,295 "rstrip": false,296 "single_word": false,297 "special": true298 },299 "50014": {300 "content": "扼",301 "lstrip": false,302 "normalized": false,303 "rstrip": false,304 "single_word": false,305 "special": true306 },307 "50015": {308 "content": "뇶",309 "lstrip": false,310 "normalized": false,311 "rstrip": false,312 "single_word": false,313 "special": true314 },315 "50016": {316 "content": "뭷",317 "lstrip": false,318 "normalized": false,319 "rstrip": false,320 "single_word": false,321 "special": true322 },323 "50017": {324 "content": "ஒ",325 "lstrip": false,326 "normalized": false,327 "rstrip": false,328 "single_word": false,329 "special": true330 },331 "50018": {332 "content": "戟",333 "lstrip": false,334 "normalized": false,335 "rstrip": false,336 "single_word": false,337 "special": true338 },339 "50019": {340 "content": "먂",341 "lstrip": false,342 "normalized": false,343 "rstrip": false,344 "single_word": false,345 "special": true346 },347 "50020": {348 "content": "찜",349 "lstrip": false,350 "normalized": false,351 "rstrip": false,352 "single_word": false,353 "special": true354 },355 "50021": {356 "content": "銎",357 "lstrip": false,358 "normalized": false,359 "rstrip": false,360 "single_word": false,361 "special": true362 },363 "50022": {364 "content": "锓",365 "lstrip": false,366 "normalized": false,367 "rstrip": false,368 "single_word": false,369 "special": true370 },371 "50023": {372 "content": "돥",373 "lstrip": false,374 "normalized": false,375 "rstrip": false,376 "single_word": false,377 "special": true378 },379 "50024": {380 "content": "迟",381 "lstrip": false,382 "normalized": false,383 "rstrip": false,384 "single_word": false,385 "special": true386 },387 "50025": {388 "content": "낔",389 "lstrip": false,390 "normalized": false,391 "rstrip": false,392 "single_word": false,393 "special": true394 },395 "50026": {396 "content": "촭",397 "lstrip": false,398 "normalized": false,399 "rstrip": false,400 "single_word": false,401 "special": true402 },403 "50027": {404 "content": "拐",405 "lstrip": false,406 "normalized": false,407 "rstrip": false,408 "single_word": false,409 "special": true410 },411 "50028": {412 "content": "蚱",413 "lstrip": false,414 "normalized": false,415 "rstrip": false,416 "single_word": false,417 "special": true418 },419 "50029": {420 "content": "둥",421 "lstrip": false,422 "normalized": false,423 "rstrip": false,424 "single_word": false,425 "special": true426 },427 "50030": {428 "content": "쑝",429 "lstrip": false,430 "normalized": false,431 "rstrip": false,432 "single_word": false,433 "special": true434 },435 "50031": {436 "content": "툝",437 "lstrip": false,438 "normalized": false,439 "rstrip": false,440 "single_word": false,441 "special": true442 },443 "50032": {444 "content": "躐",445 "lstrip": false,446 "normalized": false,447 "rstrip": false,448 "single_word": false,449 "special": true450 },451 "50033": {452 "content": "忏",453 "lstrip": false,454 "normalized": false,455 "rstrip": false,456 "single_word": false,457 "special": true458 },459 "50034": {460 "content": "借",461 "lstrip": false,462 "normalized": false,463 "rstrip": false,464 "single_word": false,465 "special": true466 },467 "50035": {468 "content": "旋",469 "lstrip": false,470 "normalized": false,471 "rstrip": false,472 "single_word": false,473 "special": true474 },475 "50036": {476 "content": "퓹",477 "lstrip": false,478 "normalized": false,479 "rstrip": false,480 "single_word": false,481 "special": true482 },483 "50037": {484 "content": "떟",485 "lstrip": false,486 "normalized": false,487 "rstrip": false,488 "single_word": false,489 "special": true490 },491 "50038": {492 "content": "耇",493 "lstrip": false,494 "normalized": false,495 "rstrip": false,496 "single_word": false,497 "special": true498 },499 "50039": {500 "content": "쀭",501 "lstrip": false,502 "normalized": false,503 "rstrip": false,504 "single_word": false,505 "special": true506 },507 "50040": {508 "content": "ੇ",509 "lstrip": false,510 "normalized": false,511 "rstrip": false,512 "single_word": false,513 "special": true514 },515 "50041": {516 "content": "酷",517 "lstrip": false,518 "normalized": false,519 "rstrip": false,520 "single_word": false,521 "special": true522 },523 "50042": {524 "content": "沱",525 "lstrip": false,526 "normalized": false,527 "rstrip": false,528 "single_word": false,529 "special": true530 },531 "50043": {532 "content": "확",533 "lstrip": false,534 "normalized": false,535 "rstrip": false,536 "single_word": false,537 "special": true538 },539 "50044": {540 "content": "ツ",541 "lstrip": false,542 "normalized": false,543 "rstrip": false,544 "single_word": false,545 "special": true546 },547 "50045": {548 "content": "縫",549 "lstrip": false,550 "normalized": false,551 "rstrip": false,552 "single_word": false,553 "special": true554 },555 "50046": {556 "content": "찄",557 "lstrip": false,558 "normalized": false,559 "rstrip": false,560 "single_word": false,561 "special": true562 },563 "50047": {564 "content": "쿵",565 "lstrip": false,566 "normalized": false,567 "rstrip": false,568 "single_word": false,569 "special": true570 },571 "50048": {572 "content": "쾜",573 "lstrip": false,574 "normalized": false,575 "rstrip": false,576 "single_word": false,577 "special": true578 },579 "50049": {580 "content": "兀",581 "lstrip": false,582 "normalized": false,583 "rstrip": false,584 "single_word": false,585 "special": true586 },587 "50050": {588 "content": "휑",589 "lstrip": false,590 "normalized": false,591 "rstrip": false,592 "single_word": false,593 "special": true594 },595 "50051": {596 "content": "찕",597 "lstrip": false,598 "normalized": false,599 "rstrip": false,600 "single_word": false,601 "special": true602 },603 "50052": {604 "content": "ఏ",605 "lstrip": false,606 "normalized": false,607 "rstrip": false,608 "single_word": false,609 "special": true610 },611 "50053": {612 "content": "」",613 "lstrip": false,614 "normalized": false,615 "rstrip": false,616 "single_word": false,617 "special": true618 },619 "50054": {620 "content": "졇",621 "lstrip": false,622 "normalized": false,623 "rstrip": false,624 "single_word": false,625 "special": true626 },627 "50055": {628 "content": "讻",629 "lstrip": false,630 "normalized": false,631 "rstrip": false,632 "single_word": false,633 "special": true634 },635 "50056": {636 "content": "閻",637 "lstrip": false,638 "normalized": false,639 "rstrip": false,640 "single_word": false,641 "special": true642 },643 "50057": {644 "content": "ઢ",645 "lstrip": false,646 "normalized": false,647 "rstrip": false,648 "single_word": false,649 "special": true650 },651 "50058": {652 "content": "쩅",653 "lstrip": false,654 "normalized": false,655 "rstrip": false,656 "single_word": false,657 "special": true658 },659 "50059": {660 "content": "쵊",661 "lstrip": false,662 "normalized": false,663 "rstrip": false,664 "single_word": false,665 "special": true666 },667 "50060": {668 "content": "콸",669 "lstrip": false,670 "normalized": false,671 "rstrip": false,672 "single_word": false,673 "special": true674 },675 "50061": {676 "content": "遹",677 "lstrip": false,678 "normalized": false,679 "rstrip": false,680 "single_word": false,681 "special": true682 },683 "50062": {684 "content": "뒐",685 "lstrip": false,686 "normalized": false,687 "rstrip": false,688 "single_word": false,689 "special": true690 },691 "50063": {692 "content": "꺃",693 "lstrip": false,694 "normalized": false,695 "rstrip": false,696 "single_word": false,697 "special": true698 },699 "50064": {700 "content": "卟",701 "lstrip": false,702 "normalized": false,703 "rstrip": false,704 "single_word": false,705 "special": true706 },707 "50065": {708 "content": "帏",709 "lstrip": false,710 "normalized": false,711 "rstrip": false,712 "single_word": false,713 "special": true714 },715 "50066": {716 "content": "缉",717 "lstrip": false,718 "normalized": false,719 "rstrip": false,720 "single_word": false,721 "special": true722 },723 "50067": {724 "content": "촸",725 "lstrip": false,726 "normalized": false,727 "rstrip": false,728 "single_word": false,729 "special": true730 },731 "50068": {732 "content": "뫉",733 "lstrip": false,734 "normalized": false,735 "rstrip": false,736 "single_word": false,737 "special": true738 },739 "50069": {740 "content": "ڧ",741 "lstrip": false,742 "normalized": false,743 "rstrip": false,744 "single_word": false,745 "special": true746 },747 "50070": {748 "content": "텔",749 "lstrip": false,750 "normalized": false,751 "rstrip": false,752 "single_word": false,753 "special": true754 },755 "50071": {756 "content": "撃",757 "lstrip": false,758 "normalized": false,759 "rstrip": false,760 "single_word": false,761 "special": true762 },763 "50072": {764 "content": "ા",765 "lstrip": false,766 "normalized": false,767 "rstrip": false,768 "single_word": false,769 "special": true770 },771 "50073": {772 "content": "繃",773 "lstrip": false,774 "normalized": false,775 "rstrip": false,776 "single_word": false,777 "special": true778 },779 "50074": {780 "content": "쨷",781 "lstrip": false,782 "normalized": false,783 "rstrip": false,784 "single_word": false,785 "special": true786 },787 "50075": {788 "content": "囟",789 "lstrip": false,790 "normalized": false,791 "rstrip": false,792 "single_word": false,793 "special": true794 },795 "50076": {796 "content": "獅",797 "lstrip": false,798 "normalized": false,799 "rstrip": false,800 "single_word": false,801 "special": true802 },803 "50077": {804 "content": "控",805 "lstrip": false,806 "normalized": false,807 "rstrip": false,808 "single_word": false,809 "special": true810 },811 "50078": {812 "content": "꼣",813 "lstrip": false,814 "normalized": false,815 "rstrip": false,816 "single_word": false,817 "special": true818 },819 "50079": {820 "content": "ڶ",821 "lstrip": false,822 "normalized": false,823 "rstrip": false,824 "single_word": false,825 "special": true826 },827 "50080": {828 "content": "涇",829 "lstrip": false,830 "normalized": false,831 "rstrip": false,832 "single_word": false,833 "special": true834 },835 "50081": {836 "content": "坩",837 "lstrip": false,838 "normalized": false,839 "rstrip": false,840 "single_word": false,841 "special": true842 },843 "50082": {844 "content": "智",845 "lstrip": false,846 "normalized": false,847 "rstrip": false,848 "single_word": false,849 "special": true850 },851 "50083": {852 "content": "괨",853 "lstrip": false,854 "normalized": false,855 "rstrip": false,856 "single_word": false,857 "special": true858 },859 "50084": {860 "content": "뛻",861 "lstrip": false,862 "normalized": false,863 "rstrip": false,864 "single_word": false,865 "special": true866 },867 "50085": {868 "content": "먈",869 "lstrip": false,870 "normalized": false,871 "rstrip": false,872 "single_word": false,873 "special": true874 },875 "50086": {876 "content": "㧐",877 "lstrip": false,878 "normalized": false,879 "rstrip": false,880 "single_word": false,881 "special": true882 },883 "50087": {884 "content": "뻁",885 "lstrip": false,886 "normalized": false,887 "rstrip": false,888 "single_word": false,889 "special": true890 },891 "50088": {892 "content": "幀",893 "lstrip": false,894 "normalized": false,895 "rstrip": false,896 "single_word": false,897 "special": true898 },899 "50089": {900 "content": "祋",901 "lstrip": false,902 "normalized": false,903 "rstrip": false,904 "single_word": false,905 "special": true906 },907 "50090": {908 "content": "꾼",909 "lstrip": false,910 "normalized": false,911 "rstrip": false,912 "single_word": false,913 "special": true914 },915 "50091": {916 "content": "婊",917 "lstrip": false,918 "normalized": false,919 "rstrip": false,920 "single_word": false,921 "special": true922 },923 "50092": {924 "content": "蕉",925 "lstrip": false,926 "normalized": false,927 "rstrip": false,928 "single_word": false,929 "special": true930 },931 "50093": {932 "content": "뜮",933 "lstrip": false,934 "normalized": false,935 "rstrip": false,936 "single_word": false,937 "special": true938 },939 "50094": {940 "content": "룦",941 "lstrip": false,942 "normalized": false,943 "rstrip": false,944 "single_word": false,945 "special": true946 },947 "50095": {948 "content": "븮",949 "lstrip": false,950 "normalized": false,951 "rstrip": false,952 "single_word": false,953 "special": true954 },955 "50096": {956 "content": "突",957 "lstrip": false,958 "normalized": false,959 "rstrip": false,960 "single_word": false,961 "special": true962 },963 "50097": {964 "content": "茁",965 "lstrip": false,966 "normalized": false,967 "rstrip": false,968 "single_word": false,969 "special": true970 },971 "50098": {972 "content": "쫦",973 "lstrip": false,974 "normalized": false,975 "rstrip": false,976 "single_word": false,977 "special": true978 },979 "50099": {980 "content": "깩",981 "lstrip": false,982 "normalized": false,983 "rstrip": false,984 "single_word": false,985 "special": true986 },987 "50100": {988 "content": "穷",989 "lstrip": false,990 "normalized": false,991 "rstrip": false,992 "single_word": false,993 "special": true994 },995 "50101": {996 "content": "邪",997 "lstrip": false,998 "normalized": false,999 "rstrip": false,1000 "single_word": false,1001 "special": true1002 },1003 "50102": {1004 "content": "궙",1005 "lstrip": false,1006 "normalized": false,1007 "rstrip": false,1008 "single_word": false,1009 "special": true1010 },1011 "50103": {1012 "content": "璧",1013 "lstrip": false,1014 "normalized": false,1015 "rstrip": false,1016 "single_word": false,1017 "special": true1018 },1019 "50104": {1020 "content": "ಟ",1021 "lstrip": false,1022 "normalized": false,1023 "rstrip": false,1024 "single_word": false,1025 "special": true1026 },1027 "50105": {1028 "content": "횕",1029 "lstrip": false,1030 "normalized": false,1031 "rstrip": false,1032 "single_word": false,1033 "special": true1034 },1035 "50106": {1036 "content": "闲",1037 "lstrip": false,1038 "normalized": false,1039 "rstrip": false,1040 "single_word": false,1041 "special": true1042 },1043 "50107": {1044 "content": "噤",1045 "lstrip": false,1046 "normalized": false,1047 "rstrip": false,1048 "single_word": false,1049 "special": true1050 },1051 "50108": {1052 "content": "앃",1053 "lstrip": false,1054 "normalized": false,1055 "rstrip": false,1056 "single_word": false,1057 "special": true1058 },1059 "50109": {1060 "content": "즷",1061 "lstrip": false,1062 "normalized": false,1063 "rstrip": false,1064 "single_word": false,1065 "special": true1066 },1067 "50110": {1068 "content": "椿",1069 "lstrip": false,1070 "normalized": false,1071 "rstrip": false,1072 "single_word": false,1073 "special": true1074 },1075 "50111": {1076 "content": "ݙ",1077 "lstrip": false,1078 "normalized": false,1079 "rstrip": false,1080 "single_word": false,1081 "special": true1082 },1083 "50112": {1084 "content": "遭",1085 "lstrip": false,1086 "normalized": false,1087 "rstrip": false,1088 "single_word": false,1089 "special": true1090 },1091 "50113": {1092 "content": "峰",1093 "lstrip": false,1094 "normalized": false,1095 "rstrip": false,1096 "single_word": false,1097 "special": true1098 },1099 "50114": {1100 "content": "剑",1101 "lstrip": false,1102 "normalized": false,1103 "rstrip": false,1104 "single_word": false,1105 "special": true1106 },1107 "50115": {1108 "content": "냺",1109 "lstrip": false,1110 "normalized": false,1111 "rstrip": false,1112 "single_word": false,1113 "special": true1114 },1115 "50116": {1116 "content": "찤",1117 "lstrip": false,1118 "normalized": false,1119 "rstrip": false,1120 "single_word": false,1121 "special": true1122 },1123 "50117": {1124 "content": "롚",1125 "lstrip": false,1126 "normalized": false,1127 "rstrip": false,1128 "single_word": false,1129 "special": true1130 },1131 "50118": {1132 "content": "퍶",1133 "lstrip": false,1134 "normalized": false,1135 "rstrip": false,1136 "single_word": false,1137 "special": true1138 },1139 "50119": {1140 "content": "걝",1141 "lstrip": false,1142 "normalized": false,1143 "rstrip": false,1144 "single_word": false,1145 "special": true1146 },1147 "50120": {1148 "content": "뭢",1149 "lstrip": false,1150 "normalized": false,1151 "rstrip": false,1152 "single_word": false,1153 "special": true1154 },1155 "50121": {1156 "content": "螬",1157 "lstrip": false,1158 "normalized": false,1159 "rstrip": false,1160 "single_word": false,1161 "special": true1162 },1163 "50122": {1164 "content": "駛",1165 "lstrip": false,1166 "normalized": false,1167 "rstrip": false,1168 "single_word": false,1169 "special": true1170 },1171 "50123": {1172 "content": "綦",1173 "lstrip": false,1174 "normalized": false,1175 "rstrip": false,1176 "single_word": false,1177 "special": true1178 },1179 "50124": {1180 "content": "Ứ",1181 "lstrip": false,1182 "normalized": false,1183 "rstrip": false,1184 "single_word": false,1185 "special": true1186 },1187 "50125": {1188 "content": "롗",1189 "lstrip": false,1190 "normalized": false,1191 "rstrip": false,1192 "single_word": false,1193 "special": true1194 },1195 "50126": {1196 "content": "Ε",1197 "lstrip": false,1198 "normalized": false,1199 "rstrip": false,1200 "single_word": false,