ViMATCHA / tokenizer_config.json
hoangphu7122002ai's picture
TeeA/ViMATCHA
5d20ab0 verified
{
"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
},
"3": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"25": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"27": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"28": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"37": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"38": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"39": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"40": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"41": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"42": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"43": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"44": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"45": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"46": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"47": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"48": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"52": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"53": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"54": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"55": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"56": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"57": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"58": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"59": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"62": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"67": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"68": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"69": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"70": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"71": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"72": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"74": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"75": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"76": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"77": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"78": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"79": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"81": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"82": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"83": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"84": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"85": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"86": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"87": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"88": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"89": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"90": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"91": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"93": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"94": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"95": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"97": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"98": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"99": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"121": {
"content": "<col>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"150": {
"content": "<row>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"17827": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17828": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17829": {
"content": "</table>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"17830": {
"content": "<table>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"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>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"processor_class": "Pix2StructProcessor",
"sep_token": "<sep>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}