{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 21, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 22, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 23, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 24, "content": "[UNK]", "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": [ 0 ], "tokens": [ "[CLS]" ] }, "[SEP]": { "id": "[SEP]", "ids": [ 22 ], "tokens": [ "[SEP]" ] } } }, "decoder": { "type": "WordPiece", "prefix": "##", "cleanup": true }, "model": { "type": "WordPiece", "unk_token": "[UNK]", "continuing_subword_prefix": "##", "max_input_chars_per_word": 100, "vocab": { "[CLS]": 0, "M": 1, "R": 2, "H": 3, "K": 4, "D": 5, "E": 6, "S": 7, "T": 8, "N": 9, "Q": 10, "C": 11, "G": 12, "P": 13, "A": 14, "V": 15, "I": 16, "F": 17, "Y": 18, "W": 19, "L": 20, "[PAD]": 21, "[SEP]": 22, "[MASK]": 23, "[UNK]": 24 } } }