peter2000's picture
add tokenizer
74911cc
raw history blame
No virus
942 Bytes
{"#": 1, "(": 2, ")": 3, "*": 4, "+": 5, "<": 6, "=": 7, ">": 8, "@": 9, "\\": 10, "_": 11, "`": 12, "a": 13, "b": 14, "c": 15, "d": 16, "e": 17, "f": 18, "g": 19, "h": 20, "i": 21, "j": 22, "k": 23, "l": 24, "m": 25, "n": 26, "o": 27, "p": 28, "q": 29, "r": 30, "s": 31, "t": 32, "u": 33, "v": 34, "w": 35, "x": 36, "y": 37, "z": 38, "£": 39, "¨": 40, "©": 41, "«": 42, "®": 43, "°": 44, "»": 45, "¼": 46, "½": 47, "á": 48, "é": 49, "ï": 50, "ñ": 51, "ò": 52, "ö": 53, "ø": 54, "ù": 55, "ü": 56, "ÿ": 57, "ā": 58, "ć": 59, "ē": 60, "ğ": 61, "ī": 62, "ō": 63, "œ": 64, "ş": 65, "š": 66, "ū": 67, "ȃ": 68, "ȏ": 69, "ʺ": 70, "ʼ": 71, "ʽ": 72, "˜": 73, "˝": 74, "̀": 75, "в": 76, "к": 77, "о": 78, "у": 79, "і": 80, "ḥ": 81, "ṭ": 82, "‐": 83, "–": 84, "—": 85, "―": 86, "’": 87, "‟": 88, "•": 89, "…": 90, "″": 91, "‽": 92, "€": 93, "™": 94, "|": 0, "[UNK]": 95, "[PAD]": 96}