{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "" }, "behavior": "Isolated", "invert": false }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 1 ], "tokens": [ "" ] }, "": { "id": "", "ids": [ 2 ], "tokens": [ "" ] } } }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "": 0, "": 1, "": 2, "": 3, "\n": 4, " ": 5, "!": 6, "\"": 7, "'": 8, ",": 9, "-": 10, ".": 11, "0": 12, "1": 13, "2": 14, "3": 15, "4": 16, "5": 17, "8": 18, ":": 19, ";": 20, "?": 21, "A": 22, "B": 23, "C": 24, "D": 25, "E": 26, "F": 27, "G": 28, "H": 29, "I": 30, "J": 31, "K": 32, "L": 33, "M": 34, "N": 35, "O": 36, "P": 37, "Q": 38, "R": 39, "S": 40, "T": 41, "U": 42, "V": 43, "W": 44, "X": 45, "Y": 46, "Z": 47, "a": 48, "b": 49, "c": 50, "d": 51, "e": 52, "f": 53, "g": 54, "h": 55, "i": 56, "j": 57, "k": 58, "l": 59, "m": 60, "n": 61, "o": 62, "p": 63, "q": 64, "r": 65, "s": 66, "t": 67, "u": 68, "v": 69, "w": 70, "x": 71, "y": 72, "z": 73, "¦": 74, "â": 75, "œ": 76, "˜": 77, "“": 78, "”": 79, "€": 80, "™": 81 }, "unk_token": "" } }