{ "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 } ], "normalizer": null, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "[\\s\\S]" }, "behavior": "Isolated", "invert": false }, "post_processor": null, "decoder": { "type": "Fuse" }, "model": { "type": "WordLevel", "vocab": { "": 0, "": 1, "\t": 2, "\n": 3, " ": 4, "!": 5, "#": 6, "%": 7, "'": 8, "(": 9, ")": 10, "*": 11, "+": 12, ",": 13, "-": 14, ".": 15, "/": 16, "0": 17, "1": 18, "2": 19, "3": 20, "4": 21, "5": 22, "6": 23, "7": 24, "8": 25, "9": 26, ":": 27, "<": 28, "=": 29, ">": 30, "A": 31, "B": 32, "C": 33, "D": 34, "E": 35, "F": 36, "G": 37, "H": 38, "I": 39, "K": 40, "L": 41, "M": 42, "O": 43, "P": 44, "Q": 45, "R": 46, "S": 47, "T": 48, "U": 49, "V": 50, "Z": 51, "[": 52, "\\": 53, "]": 54, "^": 55, "_": 56, "`": 57, "a": 58, "b": 59, "c": 60, "d": 61, "e": 62, "f": 63, "g": 64, "h": 65, "i": 66, "j": 67, "k": 68, "l": 69, "m": 70, "n": 71, "o": 72, "p": 73, "r": 74, "s": 75, "t": 76, "u": 77, "v": 78, "w": 79, "x": 80, "y": 81, "z": 82, "{": 83, "|": 84, "}": 85, "~": 86 }, "unk_token": "" } }