| { | |
| "version": "1.0", | |
| "truncation": { | |
| "direction": "Right", | |
| "max_length": 1024, | |
| "strategy": "LongestFirst", | |
| "stride": 0 | |
| }, | |
| "padding": { | |
| "strategy": { | |
| "Fixed": 1024 | |
| }, | |
| "direction": "Right", | |
| "pad_to_multiple_of": null, | |
| "pad_id": 0, | |
| "pad_type_id": 0, | |
| "pad_token": "[PAD]" | |
| }, | |
| "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, | |
| "A": 5, | |
| "T": 6, | |
| "C": 7, | |
| "G": 8, | |
| "N": 9, | |
| "AAA": 10, | |
| "AAT": 11, | |
| "AAC": 12, | |
| "AAG": 13, | |
| "ATA": 14, | |
| "ATT": 15, | |
| "ATC": 16, | |
| "ATG": 17, | |
| "ACA": 18, | |
| "ACT": 19, | |
| "ACC": 20, | |
| "ACG": 21, | |
| "AGA": 22, | |
| "AGT": 23, | |
| "AGC": 24, | |
| "AGG": 25, | |
| "TAA": 26, | |
| "TAT": 27, | |
| "TAC": 28, | |
| "TAG": 29, | |
| "TTA": 30, | |
| "TTT": 31, | |
| "TTC": 32, | |
| "TTG": 33, | |
| "TCA": 34, | |
| "TCT": 35, | |
| "TCC": 36, | |
| "TCG": 37, | |
| "TGA": 38, | |
| "TGT": 39, | |
| "TGC": 40, | |
| "TGG": 41, | |
| "CAA": 42, | |
| "CAT": 43, | |
| "CAC": 44, | |
| "CAG": 45, | |
| "CTA": 46, | |
| "CTT": 47, | |
| "CTC": 48, | |
| "CTG": 49, | |
| "CCA": 50, | |
| "CCT": 51, | |
| "CCC": 52, | |
| "CCG": 53, | |
| "CGA": 54, | |
| "CGT": 55, | |
| "CGC": 56, | |
| "CGG": 57, | |
| "GAA": 58, | |
| "GAT": 59, | |
| "GAC": 60, | |
| "GAG": 61, | |
| "GTA": 62, | |
| "GTT": 63, | |
| "GTC": 64, | |
| "GTG": 65, | |
| "GCA": 66, | |
| "GCT": 67, | |
| "GCC": 68, | |
| "GCG": 69, | |
| "GGA": 70, | |
| "GGT": 71, | |
| "GGC": 72, | |
| "GGG": 73 | |
| } | |
| } | |
| } |