{ | |
"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 | |
}, | |
"2": { | |
"content": "[CLS]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"3": { | |
"content": "[SEP]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"4": { | |
"content": "[MASK]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"5": { | |
"content": "[BOS]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"6": { | |
"content": "[EOS]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"7": { | |
"content": "[TAG]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"8": { | |
"content": "[ATTR]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"9": { | |
"content": "[COMMENT]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"10": { | |
"content": "[BASE64]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"11": { | |
"content": "[LONG]", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"additional_special_tokens": [ | |
"[BOS]", | |
"[EOS]", | |
"[TAG]", | |
"[ATTR]", | |
"[COMMENT]", | |
"[BASE64]", | |
"[LONG]" | |
], | |
"bos_token": "[BOS]", | |
"clean_up_tokenization_spaces": true, | |
"cls_token": "[CLS]", | |
"do_lower_case": false, | |
"eos_token": "[EOS]", | |
"mask_token": "[MASK]", | |
"model_max_length": 512, | |
"pad_token": "[PAD]", | |
"sep_token": "[SEP]", | |
"strip_accents": null, | |
"tokenize_chinese_chars": true, | |
"tokenizer_class": "BertTokenizer", | |
"unk_token": "[UNK]" | |
} | |