|
{ |
|
"version": "1.0", |
|
"truncation": null, |
|
"padding": null, |
|
"added_tokens": [ |
|
{ |
|
"id": 0, |
|
"content": "[PAD]", |
|
"single_word": false, |
|
"lstrip": false, |
|
"rstrip": false, |
|
"normalized": false, |
|
"special": true |
|
}, |
|
{ |
|
"id": 1, |
|
"content": "[UNK]", |
|
"single_word": false, |
|
"lstrip": false, |
|
"rstrip": false, |
|
"normalized": false, |
|
"special": true |
|
}, |
|
{ |
|
"id": 2, |
|
"content": "[CLS]", |
|
"single_word": false, |
|
"lstrip": false, |
|
"rstrip": false, |
|
"normalized": false, |
|
"special": true |
|
}, |
|
{ |
|
"id": 3, |
|
"content": "[SEP]", |
|
"single_word": false, |
|
"lstrip": false, |
|
"rstrip": false, |
|
"normalized": false, |
|
"special": true |
|
}, |
|
{ |
|
"id": 4, |
|
"content": "[MASK]", |
|
"single_word": false, |
|
"lstrip": false, |
|
"rstrip": false, |
|
"normalized": false, |
|
"special": true |
|
} |
|
], |
|
"normalizer": { |
|
"type": "BertNormalizer", |
|
"clean_text": true, |
|
"handle_chinese_chars": true, |
|
"strip_accents": null, |
|
"lowercase": false |
|
}, |
|
"pre_tokenizer": { |
|
"type": "BertPreTokenizer" |
|
}, |
|
"post_processor": { |
|
"type": "TemplateProcessing", |
|
"single": [ |
|
{ |
|
"SpecialToken": { |
|
"id": "[CLS]", |
|
"type_id": 0 |
|
} |
|
}, |
|
{ |
|
"Sequence": { |
|
"id": "A", |
|
"type_id": 0 |
|
} |
|
}, |
|
{ |
|
"SpecialToken": { |
|
"id": "[SEP]", |
|
"type_id": 0 |
|
} |
|
} |
|
], |
|
"pair": [ |
|
{ |
|
"SpecialToken": { |
|
"id": "[CLS]", |
|
"type_id": 0 |
|
} |
|
}, |
|
{ |
|
"Sequence": { |
|
"id": "A", |
|
"type_id": 0 |
|
} |
|
}, |
|
{ |
|
"SpecialToken": { |
|
"id": "[SEP]", |
|
"type_id": 0 |
|
} |
|
}, |
|
{ |
|
"Sequence": { |
|
"id": "B", |
|
"type_id": 1 |
|
} |
|
}, |
|
{ |
|
"SpecialToken": { |
|
"id": "[SEP]", |
|
"type_id": 1 |
|
} |
|
} |
|
], |
|
"special_tokens": { |
|
"[CLS]": { |
|
"id": "[CLS]", |
|
"ids": [ |
|
2 |
|
], |
|
"tokens": [ |
|
"[CLS]" |
|
] |
|
}, |
|
"[SEP]": { |
|
"id": "[SEP]", |
|
"ids": [ |
|
3 |
|
], |
|
"tokens": [ |
|
"[SEP]" |
|
] |
|
} |
|
} |
|
}, |
|
"decoder": { |
|
"type": "WordPiece", |
|
"prefix": "##", |
|
"cleanup": true |
|
}, |
|
"model": { |
|
"type": "WordPiece", |
|
"unk_token": "[UNK]", |
|
"continuing_subword_prefix": "##", |
|
"max_input_chars_per_word": 100, |
|
"vocab": { |
|
"[PAD]": 0, |
|
"[UNK]": 1, |
|
"[CLS]": 2, |
|
"[SEP]": 3, |
|
"[MASK]": 4, |
|
"AAA": 5, |
|
"AAT": 6, |
|
"AAC": 7, |
|
"AAG": 8, |
|
"ATA": 9, |
|
"ATT": 10, |
|
"ATC": 11, |
|
"ATG": 12, |
|
"ACA": 13, |
|
"ACT": 14, |
|
"ACC": 15, |
|
"ACG": 16, |
|
"AGA": 17, |
|
"AGT": 18, |
|
"AGC": 19, |
|
"AGG": 20, |
|
"TAA": 21, |
|
"TAT": 22, |
|
"TAC": 23, |
|
"TAG": 24, |
|
"TTA": 25, |
|
"TTT": 26, |
|
"TTC": 27, |
|
"TTG": 28, |
|
"TCA": 29, |
|
"TCT": 30, |
|
"TCC": 31, |
|
"TCG": 32, |
|
"TGA": 33, |
|
"TGT": 34, |
|
"TGC": 35, |
|
"TGG": 36, |
|
"CAA": 37, |
|
"CAT": 38, |
|
"CAC": 39, |
|
"CAG": 40, |
|
"CTA": 41, |
|
"CTT": 42, |
|
"CTC": 43, |
|
"CTG": 44, |
|
"CCA": 45, |
|
"CCT": 46, |
|
"CCC": 47, |
|
"CCG": 48, |
|
"CGA": 49, |
|
"CGT": 50, |
|
"CGC": 51, |
|
"CGG": 52, |
|
"GAA": 53, |
|
"GAT": 54, |
|
"GAC": 55, |
|
"GAG": 56, |
|
"GTA": 57, |
|
"GTT": 58, |
|
"GTC": 59, |
|
"GTG": 60, |
|
"GCA": 61, |
|
"GCT": 62, |
|
"GCC": 63, |
|
"GCG": 64, |
|
"GGA": 65, |
|
"GGT": 66, |
|
"GGC": 67, |
|
"GGG": 68 |
|
} |
|
} |
|
} |