{ | |
"add_bos_token": false, | |
"add_prefix_space": false, | |
"added_tokens_decoder": { | |
"0": { | |
"content": "[PAD]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"1": { | |
"content": "[CLS]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"2": { | |
"content": "[SEP]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"3": { | |
"content": "[UNK]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"50264": { | |
"content": "[MASK]", | |
"lstrip": true, | |
"normalized": true, | |
"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]", | |
"errors": "replace", | |
"mask_token": "[MASK]", | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": "[PAD]", | |
"sep_token": "[SEP]", | |
"tokenizer_class": "DebertaTokenizer", | |
"unk_token": "[UNK]", | |
"vocab_type": "gpt2" | |
} | |