AraT5_stage1 / tokenizer_config.json
ibrahimsharaf's picture
Upload tokenizer_config.json with huggingface_hub
c3789ce verified
raw
history blame
21.1 kB
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"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,
"max_length": 30,
"model_max_length": 1024,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"sp_model_kwargs": {},
"stride": 0,
"tokenizer_class": "T5Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}