Upload 4 files
Browse files- tokenizer.json +135 -0
- tokenizer_config.json +120 -0
tokenizer.json
CHANGED
|
@@ -30,6 +30,15 @@
|
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{
|
| 34 |
"id": 32000,
|
| 35 |
"content": "<extra_id_99>",
|
|
@@ -947,6 +956,132 @@
|
|
| 947 |
"rstrip": false,
|
| 948 |
"normalized": true,
|
| 949 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 950 |
}
|
| 951 |
],
|
| 952 |
"normalizer": {
|
|
|
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
},
|
| 33 |
+
{
|
| 34 |
+
"id": 10452,
|
| 35 |
+
"content": "good",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
{
|
| 43 |
"id": 32000,
|
| 44 |
"content": "<extra_id_99>",
|
|
|
|
| 956 |
"rstrip": false,
|
| 957 |
"normalized": true,
|
| 958 |
"special": false
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"id": 32102,
|
| 962 |
+
"content": "happy",
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"lstrip": false,
|
| 965 |
+
"rstrip": false,
|
| 966 |
+
"normalized": true,
|
| 967 |
+
"special": false
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"id": 32103,
|
| 971 |
+
"content": "intelligent",
|
| 972 |
+
"single_word": false,
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"rstrip": false,
|
| 975 |
+
"normalized": true,
|
| 976 |
+
"special": false
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"id": 32104,
|
| 980 |
+
"content": "response",
|
| 981 |
+
"single_word": false,
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"normalized": true,
|
| 985 |
+
"special": false
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"id": 32105,
|
| 989 |
+
"content": "environment",
|
| 990 |
+
"single_word": false,
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"normalized": true,
|
| 994 |
+
"special": false
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"id": 32106,
|
| 998 |
+
"content": "amazeballs",
|
| 999 |
+
"single_word": false,
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"normalized": true,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"id": 32107,
|
| 1007 |
+
"content": "cryptocurrency",
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"lstrip": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"normalized": true,
|
| 1012 |
+
"special": false
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"id": 32108,
|
| 1016 |
+
"content": "webinar",
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"lstrip": false,
|
| 1019 |
+
"rstrip": false,
|
| 1020 |
+
"normalized": true,
|
| 1021 |
+
"special": false
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"id": 32109,
|
| 1025 |
+
"content": "vlog",
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"lstrip": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"normalized": true,
|
| 1030 |
+
"special": false
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"id": 32110,
|
| 1034 |
+
"content": "upcycle",
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"lstrip": false,
|
| 1037 |
+
"rstrip": false,
|
| 1038 |
+
"normalized": true,
|
| 1039 |
+
"special": false
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"id": 32111,
|
| 1043 |
+
"content": "photobomb",
|
| 1044 |
+
"single_word": false,
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"rstrip": false,
|
| 1047 |
+
"normalized": true,
|
| 1048 |
+
"special": false
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"id": 32112,
|
| 1052 |
+
"content": "facepalm",
|
| 1053 |
+
"single_word": false,
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"normalized": true,
|
| 1057 |
+
"special": false
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"id": 32113,
|
| 1061 |
+
"content": "crowdfunding",
|
| 1062 |
+
"single_word": false,
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"normalized": true,
|
| 1066 |
+
"special": false
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"id": 32114,
|
| 1070 |
+
"content": "bromance",
|
| 1071 |
+
"single_word": false,
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"normalized": true,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"id": 32115,
|
| 1079 |
+
"content": "hangry",
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"lstrip": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"normalized": true,
|
| 1084 |
+
"special": false
|
| 1085 |
}
|
| 1086 |
],
|
| 1087 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -24,6 +24,14 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"32000": {
|
| 28 |
"content": "<extra_id_99>",
|
| 29 |
"lstrip": false,
|
|
@@ -839,6 +847,118 @@
|
|
| 839 |
"rstrip": false,
|
| 840 |
"single_word": false,
|
| 841 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 842 |
}
|
| 843 |
},
|
| 844 |
"additional_special_tokens": [
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"10452": {
|
| 28 |
+
"content": "good",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
"32000": {
|
| 36 |
"content": "<extra_id_99>",
|
| 37 |
"lstrip": false,
|
|
|
|
| 847 |
"rstrip": false,
|
| 848 |
"single_word": false,
|
| 849 |
"special": false
|
| 850 |
+
},
|
| 851 |
+
"32102": {
|
| 852 |
+
"content": "happy",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"32103": {
|
| 860 |
+
"content": "intelligent",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"32104": {
|
| 868 |
+
"content": "response",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"32105": {
|
| 876 |
+
"content": "environment",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"32106": {
|
| 884 |
+
"content": "amazeballs",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"32107": {
|
| 892 |
+
"content": "cryptocurrency",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"32108": {
|
| 900 |
+
"content": "webinar",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"32109": {
|
| 908 |
+
"content": "vlog",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"32110": {
|
| 916 |
+
"content": "upcycle",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"32111": {
|
| 924 |
+
"content": "photobomb",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
},
|
| 931 |
+
"32112": {
|
| 932 |
+
"content": "facepalm",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": true,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": false
|
| 938 |
+
},
|
| 939 |
+
"32113": {
|
| 940 |
+
"content": "crowdfunding",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": true,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": false
|
| 946 |
+
},
|
| 947 |
+
"32114": {
|
| 948 |
+
"content": "bromance",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": true,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": false
|
| 954 |
+
},
|
| 955 |
+
"32115": {
|
| 956 |
+
"content": "hangry",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": true,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": false
|
| 962 |
}
|
| 963 |
},
|
| 964 |
"additional_special_tokens": [
|