t5-sp-bbpe-nsmc / tokenizer_config.json
seriouspark's picture
Upload tokenizer
b6a69d4 verified
raw
history blame
20.6 kB
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31900": {
"content": "<extra_id_99>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31901": {
"content": "<extra_id_98>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31902": {
"content": "<extra_id_97>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31903": {
"content": "<extra_id_96>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31904": {
"content": "<extra_id_95>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31905": {
"content": "<extra_id_94>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31906": {
"content": "<extra_id_93>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31907": {
"content": "<extra_id_92>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31908": {
"content": "<extra_id_91>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31909": {
"content": "<extra_id_90>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31910": {
"content": "<extra_id_89>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31911": {
"content": "<extra_id_88>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31912": {
"content": "<extra_id_87>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31913": {
"content": "<extra_id_86>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31914": {
"content": "<extra_id_85>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31915": {
"content": "<extra_id_84>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31916": {
"content": "<extra_id_83>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31917": {
"content": "<extra_id_82>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31918": {
"content": "<extra_id_81>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31919": {
"content": "<extra_id_80>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31920": {
"content": "<extra_id_79>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31921": {
"content": "<extra_id_78>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31922": {
"content": "<extra_id_77>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31923": {
"content": "<extra_id_76>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31924": {
"content": "<extra_id_75>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31925": {
"content": "<extra_id_74>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31926": {
"content": "<extra_id_73>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31927": {
"content": "<extra_id_72>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31928": {
"content": "<extra_id_71>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31929": {
"content": "<extra_id_70>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31930": {
"content": "<extra_id_69>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31931": {
"content": "<extra_id_68>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31932": {
"content": "<extra_id_67>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31933": {
"content": "<extra_id_66>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31934": {
"content": "<extra_id_65>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31935": {
"content": "<extra_id_64>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31936": {
"content": "<extra_id_63>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31937": {
"content": "<extra_id_62>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31938": {
"content": "<extra_id_61>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31939": {
"content": "<extra_id_60>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31940": {
"content": "<extra_id_59>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31941": {
"content": "<extra_id_58>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31942": {
"content": "<extra_id_57>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31943": {
"content": "<extra_id_56>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31944": {
"content": "<extra_id_55>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31945": {
"content": "<extra_id_54>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31946": {
"content": "<extra_id_53>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31947": {
"content": "<extra_id_52>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31948": {
"content": "<extra_id_51>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31949": {
"content": "<extra_id_50>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31950": {
"content": "<extra_id_49>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31951": {
"content": "<extra_id_48>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31952": {
"content": "<extra_id_47>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31953": {
"content": "<extra_id_46>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31954": {
"content": "<extra_id_45>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31955": {
"content": "<extra_id_44>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31956": {
"content": "<extra_id_43>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31957": {
"content": "<extra_id_42>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31958": {
"content": "<extra_id_41>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31959": {
"content": "<extra_id_40>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31960": {
"content": "<extra_id_39>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31961": {
"content": "<extra_id_38>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31962": {
"content": "<extra_id_37>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31963": {
"content": "<extra_id_36>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31964": {
"content": "<extra_id_35>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31965": {
"content": "<extra_id_34>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31966": {
"content": "<extra_id_33>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31967": {
"content": "<extra_id_32>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31968": {
"content": "<extra_id_31>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31969": {
"content": "<extra_id_30>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31970": {
"content": "<extra_id_29>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31971": {
"content": "<extra_id_28>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31972": {
"content": "<extra_id_27>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31973": {
"content": "<extra_id_26>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31974": {
"content": "<extra_id_25>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31975": {
"content": "<extra_id_24>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31976": {
"content": "<extra_id_23>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31977": {
"content": "<extra_id_22>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31978": {
"content": "<extra_id_21>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31979": {
"content": "<extra_id_20>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31980": {
"content": "<extra_id_19>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31981": {
"content": "<extra_id_18>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31982": {
"content": "<extra_id_17>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31983": {
"content": "<extra_id_16>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31984": {
"content": "<extra_id_15>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31985": {
"content": "<extra_id_14>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31986": {
"content": "<extra_id_13>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31987": {
"content": "<extra_id_12>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31988": {
"content": "<extra_id_11>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31989": {
"content": "<extra_id_10>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31990": {
"content": "<extra_id_9>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31991": {
"content": "<extra_id_8>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31992": {
"content": "<extra_id_7>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31993": {
"content": "<extra_id_6>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31994": {
"content": "<extra_id_5>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31995": {
"content": "<extra_id_4>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31996": {
"content": "<extra_id_3>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31997": {
"content": "<extra_id_2>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31998": {
"content": "<extra_id_1>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31999": {
"content": "<extra_id_0>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}