Upload tokenizer
Browse files- tokenizer.json +576 -0
- tokenizer_config.json +512 -0
tokenizer.json
CHANGED
|
@@ -30,6 +30,24 @@
|
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{
|
| 34 |
"id": 32000,
|
| 35 |
"content": "<extra_id_99>",
|
|
@@ -929,6 +947,564 @@
|
|
| 929 |
"rstrip": false,
|
| 930 |
"normalized": false,
|
| 931 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 932 |
}
|
| 933 |
],
|
| 934 |
"normalizer": {
|
|
|
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
| 33 |
+
{
|
| 34 |
+
"id": 14775,
|
| 35 |
+
"content": "ACC",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 22029,
|
| 44 |
+
"content": "ACA",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
{
|
| 52 |
"id": 32000,
|
| 53 |
"content": "<extra_id_99>",
|
|
|
|
| 947 |
"rstrip": false,
|
| 948 |
"normalized": false,
|
| 949 |
"special": true
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"id": 32100,
|
| 953 |
+
"content": "UUU",
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"lstrip": false,
|
| 956 |
+
"rstrip": false,
|
| 957 |
+
"normalized": true,
|
| 958 |
+
"special": false
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"id": 32101,
|
| 962 |
+
"content": "UUC",
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"lstrip": false,
|
| 965 |
+
"rstrip": false,
|
| 966 |
+
"normalized": true,
|
| 967 |
+
"special": false
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"id": 32102,
|
| 971 |
+
"content": "UUA",
|
| 972 |
+
"single_word": false,
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"rstrip": false,
|
| 975 |
+
"normalized": true,
|
| 976 |
+
"special": false
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"id": 32103,
|
| 980 |
+
"content": "UUG",
|
| 981 |
+
"single_word": false,
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"normalized": true,
|
| 985 |
+
"special": false
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"id": 32104,
|
| 989 |
+
"content": "CUU",
|
| 990 |
+
"single_word": false,
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"normalized": true,
|
| 994 |
+
"special": false
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"id": 32105,
|
| 998 |
+
"content": "CUC",
|
| 999 |
+
"single_word": false,
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"normalized": true,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"id": 32106,
|
| 1007 |
+
"content": "CUA",
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"lstrip": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"normalized": true,
|
| 1012 |
+
"special": false
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"id": 32107,
|
| 1016 |
+
"content": "CUG",
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"lstrip": false,
|
| 1019 |
+
"rstrip": false,
|
| 1020 |
+
"normalized": true,
|
| 1021 |
+
"special": false
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"id": 32108,
|
| 1025 |
+
"content": "AUU",
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"lstrip": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"normalized": true,
|
| 1030 |
+
"special": false
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"id": 32109,
|
| 1034 |
+
"content": "AUC",
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"lstrip": false,
|
| 1037 |
+
"rstrip": false,
|
| 1038 |
+
"normalized": true,
|
| 1039 |
+
"special": false
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"id": 32110,
|
| 1043 |
+
"content": "AUA",
|
| 1044 |
+
"single_word": false,
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"rstrip": false,
|
| 1047 |
+
"normalized": true,
|
| 1048 |
+
"special": false
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"id": 32111,
|
| 1052 |
+
"content": "AUG",
|
| 1053 |
+
"single_word": false,
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"normalized": true,
|
| 1057 |
+
"special": false
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"id": 32112,
|
| 1061 |
+
"content": "GUU",
|
| 1062 |
+
"single_word": false,
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"normalized": true,
|
| 1066 |
+
"special": false
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"id": 32113,
|
| 1070 |
+
"content": "GUC",
|
| 1071 |
+
"single_word": false,
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"normalized": true,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"id": 32114,
|
| 1079 |
+
"content": "GUA",
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"lstrip": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"normalized": true,
|
| 1084 |
+
"special": false
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"id": 32115,
|
| 1088 |
+
"content": "GUG",
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"lstrip": false,
|
| 1091 |
+
"rstrip": false,
|
| 1092 |
+
"normalized": true,
|
| 1093 |
+
"special": false
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"id": 32116,
|
| 1097 |
+
"content": "UCU",
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"lstrip": false,
|
| 1100 |
+
"rstrip": false,
|
| 1101 |
+
"normalized": true,
|
| 1102 |
+
"special": false
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"id": 32117,
|
| 1106 |
+
"content": "UCC",
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"lstrip": false,
|
| 1109 |
+
"rstrip": false,
|
| 1110 |
+
"normalized": true,
|
| 1111 |
+
"special": false
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"id": 32118,
|
| 1115 |
+
"content": "UCA",
|
| 1116 |
+
"single_word": false,
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"rstrip": false,
|
| 1119 |
+
"normalized": true,
|
| 1120 |
+
"special": false
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"id": 32119,
|
| 1124 |
+
"content": "UCG",
|
| 1125 |
+
"single_word": false,
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"normalized": true,
|
| 1129 |
+
"special": false
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"id": 32120,
|
| 1133 |
+
"content": "CCU",
|
| 1134 |
+
"single_word": false,
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"normalized": true,
|
| 1138 |
+
"special": false
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"id": 32121,
|
| 1142 |
+
"content": "CCC",
|
| 1143 |
+
"single_word": false,
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"normalized": true,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"id": 32122,
|
| 1151 |
+
"content": "CCA",
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"lstrip": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"normalized": true,
|
| 1156 |
+
"special": false
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"id": 32123,
|
| 1160 |
+
"content": "CCG",
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"lstrip": false,
|
| 1163 |
+
"rstrip": false,
|
| 1164 |
+
"normalized": true,
|
| 1165 |
+
"special": false
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"id": 32124,
|
| 1169 |
+
"content": "ACU",
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"lstrip": false,
|
| 1172 |
+
"rstrip": false,
|
| 1173 |
+
"normalized": true,
|
| 1174 |
+
"special": false
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"id": 32125,
|
| 1178 |
+
"content": "ACG",
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"lstrip": false,
|
| 1181 |
+
"rstrip": false,
|
| 1182 |
+
"normalized": true,
|
| 1183 |
+
"special": false
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"id": 32126,
|
| 1187 |
+
"content": "GCU",
|
| 1188 |
+
"single_word": false,
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"rstrip": false,
|
| 1191 |
+
"normalized": true,
|
| 1192 |
+
"special": false
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"id": 32127,
|
| 1196 |
+
"content": "GCC",
|
| 1197 |
+
"single_word": false,
|
| 1198 |
+
"lstrip": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"normalized": true,
|
| 1201 |
+
"special": false
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"id": 32128,
|
| 1205 |
+
"content": "GCA",
|
| 1206 |
+
"single_word": false,
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"rstrip": false,
|
| 1209 |
+
"normalized": true,
|
| 1210 |
+
"special": false
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"id": 32129,
|
| 1214 |
+
"content": "GCG",
|
| 1215 |
+
"single_word": false,
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"normalized": true,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"id": 32130,
|
| 1223 |
+
"content": "UAU",
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"lstrip": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"normalized": true,
|
| 1228 |
+
"special": false
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"id": 32131,
|
| 1232 |
+
"content": "UAC",
|
| 1233 |
+
"single_word": false,
|
| 1234 |
+
"lstrip": false,
|
| 1235 |
+
"rstrip": false,
|
| 1236 |
+
"normalized": true,
|
| 1237 |
+
"special": false
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"id": 32132,
|
| 1241 |
+
"content": "UAA",
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"lstrip": false,
|
| 1244 |
+
"rstrip": false,
|
| 1245 |
+
"normalized": true,
|
| 1246 |
+
"special": false
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"id": 32133,
|
| 1250 |
+
"content": "UAG",
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"lstrip": false,
|
| 1253 |
+
"rstrip": false,
|
| 1254 |
+
"normalized": true,
|
| 1255 |
+
"special": false
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"id": 32134,
|
| 1259 |
+
"content": "CAU",
|
| 1260 |
+
"single_word": false,
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"rstrip": false,
|
| 1263 |
+
"normalized": true,
|
| 1264 |
+
"special": false
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"id": 32135,
|
| 1268 |
+
"content": "CAC",
|
| 1269 |
+
"single_word": false,
|
| 1270 |
+
"lstrip": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"normalized": true,
|
| 1273 |
+
"special": false
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"id": 32136,
|
| 1277 |
+
"content": "CAA",
|
| 1278 |
+
"single_word": false,
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"rstrip": false,
|
| 1281 |
+
"normalized": true,
|
| 1282 |
+
"special": false
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"id": 32137,
|
| 1286 |
+
"content": "CAG",
|
| 1287 |
+
"single_word": false,
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"normalized": true,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"id": 32138,
|
| 1295 |
+
"content": "AAU",
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"lstrip": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"normalized": true,
|
| 1300 |
+
"special": false
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"id": 32139,
|
| 1304 |
+
"content": "AAC",
|
| 1305 |
+
"single_word": false,
|
| 1306 |
+
"lstrip": false,
|
| 1307 |
+
"rstrip": false,
|
| 1308 |
+
"normalized": true,
|
| 1309 |
+
"special": false
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"id": 32140,
|
| 1313 |
+
"content": "AAA",
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"lstrip": false,
|
| 1316 |
+
"rstrip": false,
|
| 1317 |
+
"normalized": true,
|
| 1318 |
+
"special": false
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"id": 32141,
|
| 1322 |
+
"content": "AAG",
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"lstrip": false,
|
| 1325 |
+
"rstrip": false,
|
| 1326 |
+
"normalized": true,
|
| 1327 |
+
"special": false
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"id": 32142,
|
| 1331 |
+
"content": "GAU",
|
| 1332 |
+
"single_word": false,
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"rstrip": false,
|
| 1335 |
+
"normalized": true,
|
| 1336 |
+
"special": false
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"id": 32143,
|
| 1340 |
+
"content": "GAC",
|
| 1341 |
+
"single_word": false,
|
| 1342 |
+
"lstrip": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"normalized": true,
|
| 1345 |
+
"special": false
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"id": 32144,
|
| 1349 |
+
"content": "GAA",
|
| 1350 |
+
"single_word": false,
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"rstrip": false,
|
| 1353 |
+
"normalized": true,
|
| 1354 |
+
"special": false
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"id": 32145,
|
| 1358 |
+
"content": "GAG",
|
| 1359 |
+
"single_word": false,
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"normalized": true,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"id": 32146,
|
| 1367 |
+
"content": "UGU",
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"lstrip": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"normalized": true,
|
| 1372 |
+
"special": false
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"id": 32147,
|
| 1376 |
+
"content": "UGC",
|
| 1377 |
+
"single_word": false,
|
| 1378 |
+
"lstrip": false,
|
| 1379 |
+
"rstrip": false,
|
| 1380 |
+
"normalized": true,
|
| 1381 |
+
"special": false
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"id": 32148,
|
| 1385 |
+
"content": "UGA",
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"lstrip": false,
|
| 1388 |
+
"rstrip": false,
|
| 1389 |
+
"normalized": true,
|
| 1390 |
+
"special": false
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"id": 32149,
|
| 1394 |
+
"content": "UGG",
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"lstrip": false,
|
| 1397 |
+
"rstrip": false,
|
| 1398 |
+
"normalized": true,
|
| 1399 |
+
"special": false
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"id": 32150,
|
| 1403 |
+
"content": "CGU",
|
| 1404 |
+
"single_word": false,
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"rstrip": false,
|
| 1407 |
+
"normalized": true,
|
| 1408 |
+
"special": false
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"id": 32151,
|
| 1412 |
+
"content": "CGC",
|
| 1413 |
+
"single_word": false,
|
| 1414 |
+
"lstrip": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"normalized": true,
|
| 1417 |
+
"special": false
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"id": 32152,
|
| 1421 |
+
"content": "CGA",
|
| 1422 |
+
"single_word": false,
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"rstrip": false,
|
| 1425 |
+
"normalized": true,
|
| 1426 |
+
"special": false
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"id": 32153,
|
| 1430 |
+
"content": "CGG",
|
| 1431 |
+
"single_word": false,
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"normalized": true,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"id": 32154,
|
| 1439 |
+
"content": "AGU",
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"lstrip": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"normalized": true,
|
| 1444 |
+
"special": false
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"id": 32155,
|
| 1448 |
+
"content": "AGC",
|
| 1449 |
+
"single_word": false,
|
| 1450 |
+
"lstrip": false,
|
| 1451 |
+
"rstrip": false,
|
| 1452 |
+
"normalized": true,
|
| 1453 |
+
"special": false
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"id": 32156,
|
| 1457 |
+
"content": "AGA",
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"lstrip": false,
|
| 1460 |
+
"rstrip": false,
|
| 1461 |
+
"normalized": true,
|
| 1462 |
+
"special": false
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"id": 32157,
|
| 1466 |
+
"content": "AGG",
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"lstrip": false,
|
| 1469 |
+
"rstrip": false,
|
| 1470 |
+
"normalized": true,
|
| 1471 |
+
"special": false
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"id": 32158,
|
| 1475 |
+
"content": "GGU",
|
| 1476 |
+
"single_word": false,
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"rstrip": false,
|
| 1479 |
+
"normalized": true,
|
| 1480 |
+
"special": false
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"id": 32159,
|
| 1484 |
+
"content": "GGC",
|
| 1485 |
+
"single_word": false,
|
| 1486 |
+
"lstrip": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"normalized": true,
|
| 1489 |
+
"special": false
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"id": 32160,
|
| 1493 |
+
"content": "GGA",
|
| 1494 |
+
"single_word": false,
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"rstrip": false,
|
| 1497 |
+
"normalized": true,
|
| 1498 |
+
"special": false
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"id": 32161,
|
| 1502 |
+
"content": "GGG",
|
| 1503 |
+
"single_word": false,
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"normalized": true,
|
| 1507 |
+
"special": false
|
| 1508 |
}
|
| 1509 |
],
|
| 1510 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -24,6 +24,22 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"32000": {
|
| 28 |
"content": "<extra_id_99>",
|
| 29 |
"lstrip": false,
|
|
@@ -823,6 +839,502 @@
|
|
| 823 |
"rstrip": false,
|
| 824 |
"single_word": false,
|
| 825 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 826 |
}
|
| 827 |
},
|
| 828 |
"additional_special_tokens": [
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"14775": {
|
| 28 |
+
"content": "ACC",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"22029": {
|
| 36 |
+
"content": "ACA",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
"32000": {
|
| 44 |
"content": "<extra_id_99>",
|
| 45 |
"lstrip": false,
|
|
|
|
| 839 |
"rstrip": false,
|
| 840 |
"single_word": false,
|
| 841 |
"special": true
|
| 842 |
+
},
|
| 843 |
+
"32100": {
|
| 844 |
+
"content": "UUU",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"32101": {
|
| 852 |
+
"content": "UUC",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"32102": {
|
| 860 |
+
"content": "UUA",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"32103": {
|
| 868 |
+
"content": "UUG",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"32104": {
|
| 876 |
+
"content": "CUU",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"32105": {
|
| 884 |
+
"content": "CUC",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"32106": {
|
| 892 |
+
"content": "CUA",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"32107": {
|
| 900 |
+
"content": "CUG",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"32108": {
|
| 908 |
+
"content": "AUU",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"32109": {
|
| 916 |
+
"content": "AUC",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"32110": {
|
| 924 |
+
"content": "AUA",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
},
|
| 931 |
+
"32111": {
|
| 932 |
+
"content": "AUG",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": true,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": false
|
| 938 |
+
},
|
| 939 |
+
"32112": {
|
| 940 |
+
"content": "GUU",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": true,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": false
|
| 946 |
+
},
|
| 947 |
+
"32113": {
|
| 948 |
+
"content": "GUC",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": true,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": false
|
| 954 |
+
},
|
| 955 |
+
"32114": {
|
| 956 |
+
"content": "GUA",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": true,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": false
|
| 962 |
+
},
|
| 963 |
+
"32115": {
|
| 964 |
+
"content": "GUG",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": true,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": false
|
| 970 |
+
},
|
| 971 |
+
"32116": {
|
| 972 |
+
"content": "UCU",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": true,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": false
|
| 978 |
+
},
|
| 979 |
+
"32117": {
|
| 980 |
+
"content": "UCC",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": true,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": false
|
| 986 |
+
},
|
| 987 |
+
"32118": {
|
| 988 |
+
"content": "UCA",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": true,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": false
|
| 994 |
+
},
|
| 995 |
+
"32119": {
|
| 996 |
+
"content": "UCG",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": true,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": false
|
| 1002 |
+
},
|
| 1003 |
+
"32120": {
|
| 1004 |
+
"content": "CCU",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": true,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": false
|
| 1010 |
+
},
|
| 1011 |
+
"32121": {
|
| 1012 |
+
"content": "CCC",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": true,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": false
|
| 1018 |
+
},
|
| 1019 |
+
"32122": {
|
| 1020 |
+
"content": "CCA",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": true,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": false
|
| 1026 |
+
},
|
| 1027 |
+
"32123": {
|
| 1028 |
+
"content": "CCG",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": true,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": false
|
| 1034 |
+
},
|
| 1035 |
+
"32124": {
|
| 1036 |
+
"content": "ACU",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": true,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": false
|
| 1042 |
+
},
|
| 1043 |
+
"32125": {
|
| 1044 |
+
"content": "ACG",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": true,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": false
|
| 1050 |
+
},
|
| 1051 |
+
"32126": {
|
| 1052 |
+
"content": "GCU",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": true,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": false
|
| 1058 |
+
},
|
| 1059 |
+
"32127": {
|
| 1060 |
+
"content": "GCC",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": true,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": false
|
| 1066 |
+
},
|
| 1067 |
+
"32128": {
|
| 1068 |
+
"content": "GCA",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": true,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": false
|
| 1074 |
+
},
|
| 1075 |
+
"32129": {
|
| 1076 |
+
"content": "GCG",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": true,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": false
|
| 1082 |
+
},
|
| 1083 |
+
"32130": {
|
| 1084 |
+
"content": "UAU",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": true,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": false
|
| 1090 |
+
},
|
| 1091 |
+
"32131": {
|
| 1092 |
+
"content": "UAC",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": true,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": false
|
| 1098 |
+
},
|
| 1099 |
+
"32132": {
|
| 1100 |
+
"content": "UAA",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": true,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": false
|
| 1106 |
+
},
|
| 1107 |
+
"32133": {
|
| 1108 |
+
"content": "UAG",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": true,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": false
|
| 1114 |
+
},
|
| 1115 |
+
"32134": {
|
| 1116 |
+
"content": "CAU",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": true,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": false
|
| 1122 |
+
},
|
| 1123 |
+
"32135": {
|
| 1124 |
+
"content": "CAC",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": true,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": false
|
| 1130 |
+
},
|
| 1131 |
+
"32136": {
|
| 1132 |
+
"content": "CAA",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": true,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": false
|
| 1138 |
+
},
|
| 1139 |
+
"32137": {
|
| 1140 |
+
"content": "CAG",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": true,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": false
|
| 1146 |
+
},
|
| 1147 |
+
"32138": {
|
| 1148 |
+
"content": "AAU",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": true,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": false
|
| 1154 |
+
},
|
| 1155 |
+
"32139": {
|
| 1156 |
+
"content": "AAC",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": true,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": false
|
| 1162 |
+
},
|
| 1163 |
+
"32140": {
|
| 1164 |
+
"content": "AAA",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": true,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": false
|
| 1170 |
+
},
|
| 1171 |
+
"32141": {
|
| 1172 |
+
"content": "AAG",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": true,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": false
|
| 1178 |
+
},
|
| 1179 |
+
"32142": {
|
| 1180 |
+
"content": "GAU",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": true,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": false
|
| 1186 |
+
},
|
| 1187 |
+
"32143": {
|
| 1188 |
+
"content": "GAC",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": true,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": false
|
| 1194 |
+
},
|
| 1195 |
+
"32144": {
|
| 1196 |
+
"content": "GAA",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": true,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": false
|
| 1202 |
+
},
|
| 1203 |
+
"32145": {
|
| 1204 |
+
"content": "GAG",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": true,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": false
|
| 1210 |
+
},
|
| 1211 |
+
"32146": {
|
| 1212 |
+
"content": "UGU",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": true,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": false
|
| 1218 |
+
},
|
| 1219 |
+
"32147": {
|
| 1220 |
+
"content": "UGC",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": true,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": false
|
| 1226 |
+
},
|
| 1227 |
+
"32148": {
|
| 1228 |
+
"content": "UGA",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": true,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": false
|
| 1234 |
+
},
|
| 1235 |
+
"32149": {
|
| 1236 |
+
"content": "UGG",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": true,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": false
|
| 1242 |
+
},
|
| 1243 |
+
"32150": {
|
| 1244 |
+
"content": "CGU",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": true,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": false
|
| 1250 |
+
},
|
| 1251 |
+
"32151": {
|
| 1252 |
+
"content": "CGC",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": true,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": false
|
| 1258 |
+
},
|
| 1259 |
+
"32152": {
|
| 1260 |
+
"content": "CGA",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": true,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": false
|
| 1266 |
+
},
|
| 1267 |
+
"32153": {
|
| 1268 |
+
"content": "CGG",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": true,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": false
|
| 1274 |
+
},
|
| 1275 |
+
"32154": {
|
| 1276 |
+
"content": "AGU",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": true,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": false
|
| 1282 |
+
},
|
| 1283 |
+
"32155": {
|
| 1284 |
+
"content": "AGC",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": true,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": false
|
| 1290 |
+
},
|
| 1291 |
+
"32156": {
|
| 1292 |
+
"content": "AGA",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": true,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": false
|
| 1298 |
+
},
|
| 1299 |
+
"32157": {
|
| 1300 |
+
"content": "AGG",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": true,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": false
|
| 1306 |
+
},
|
| 1307 |
+
"32158": {
|
| 1308 |
+
"content": "GGU",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": true,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": false
|
| 1314 |
+
},
|
| 1315 |
+
"32159": {
|
| 1316 |
+
"content": "GGC",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": true,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": false
|
| 1322 |
+
},
|
| 1323 |
+
"32160": {
|
| 1324 |
+
"content": "GGA",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": true,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": false
|
| 1330 |
+
},
|
| 1331 |
+
"32161": {
|
| 1332 |
+
"content": "GGG",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": true,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": false
|
| 1338 |
}
|
| 1339 |
},
|
| 1340 |
"additional_special_tokens": [
|