{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "special": true, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 1, "special": true, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 2, "special": true, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 3, "special": true, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 4, "special": true, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "NFD" }, { "type": "Lowercase" }, { "type": "StripAccents" } ] }, "pre_tokenizer": { "type": "Whitespace" }, "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": [ 1 ], "tokens": [ "[CLS]" ] }, "[SEP]": { "id": "[SEP]", "ids": [ 2 ], "tokens": [ "[SEP]" ] } } }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "[UNK]": 0, "[CLS]": 1, "[SEP]": 2, "[PAD]": 3, "[MASK]": 4, ".": 5, "nothing": 6, "fio2": 7, "ph": 8, "paco2": 9, "pao2": 10, "hct": 11, "k": 12, "creatinine": 13, "platelets": 14, "bun": 15, "mg": 16, "hco3": 17, "na": 18, "glucose": 19, "wbc": 20, "lactate": 21, "sao2": 22, "ast": 23, "bilirubin": 24, "alt": 25 }, "unk_token": "[UNK]" } }