deberta-v3-base-japanese / tokenizer_config.json
nobu-g's picture
first commit
9553bb4 verified
{
"added_tokens_decoder": {
"96867": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96868": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96869": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96870": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"96871": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"split_by_punct": false,
"tokenizer_class": "DebertaV2Tokenizer",
"unk_token": "[UNK]"
}