{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[PAD]", "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 }, { "id": 6, "content": "A", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 7, "content": "B", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 8, "content": "C", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 9, "content": "D", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 10, "content": "E", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 11, "content": "F", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 12, "content": "G", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 13, "content": "H", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 14, "content": "I", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 15, "content": "J", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 16, "content": "K", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 17, "content": "L", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 18, "content": "M", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 19, "content": "N", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 20, "content": "O", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 21, "content": "P", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 22, "content": "Q", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 23, "content": "R", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 24, "content": "S", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 25, "content": "T", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 26, "content": "U", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 27, "content": "V", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 28, "content": "W", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 29, "content": "X", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 30, "content": "Y", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 31, "content": "Z", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 32, "content": "a", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 33, "content": "b", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 34, "content": "c", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 35, "content": "d", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 36, "content": "e", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 37, "content": "f", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 38, "content": "g", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 39, "content": "h", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 40, "content": "i", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 41, "content": "j", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 42, "content": "k", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 43, "content": "l", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 44, "content": "m", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 45, "content": "n", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 46, "content": "o", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 47, "content": "p", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 48, "content": "q", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 49, "content": "r", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 50, "content": "s", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 51, "content": "t", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 52, "content": "u", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 53, "content": "v", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 54, "content": "w", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 55, "content": "x", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 56, "content": "y", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 57, "content": "z", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 58, "content": "0", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 59, "content": "1", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 60, "content": "2", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 61, "content": "3", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 62, "content": "4", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 63, "content": "5", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 64, "content": "6", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 65, "content": "7", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 66, "content": "8", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 67, "content": "9", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 68, "content": "=", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 69, "content": "#", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 70, "content": ":", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 71, "content": "+", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 72, "content": "-", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 73, "content": "[", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 74, "content": "]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 75, "content": "(", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 76, "content": ")", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 77, "content": "/", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 78, "content": "\\", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 79, "content": "@", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 80, "content": ".", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 81, "content": "%", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "NFD" }, { "type": "Strip", "strip_left": true, "strip_right": true } ] }, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "A-Za-z0-9=#:+\\-\\[\\]()/\\\\@.%" }, "behavior": "Isolated", "invert": false }, "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": "Strip", "content": " ", "start": 0, "stop": 0 }, "model": { "type": "WordLevel", "vocab": { "[UNK]": 0, "[PAD]": 1, "[CLS]": 2, "[SEP]": 3, "[MASK]": 4, "CC": 5 }, "unk_token": "[UNK]" } }