MagedSaeed's picture
Upload tokenizer
ae541cd verified
raw
history blame contribute delete
754 Bytes
{"[UNK]": 0, "[PAD]": 1, "[BOS]": 2, "[EOS]": 3, "[SEP]": 4, "م": 5, "ن": 6, " ": 7, "د": 8, "و": 9, "ح": 10, "ة": 11, "ا": 12, "ص": 13, "ت": 14, "ذ": 15, "ئ": 16, "ب": 17, "ه": 18, "ل": 19, "س": 20, "إ": 21, "ق": 22, "ر": 23, "ء": 24, "ف": 25, "خ": 26, "َ": 27, "ز": 28, "ِ": 29, "ع": 30, "ٍ": 31, "ك": 32, "ي": 33, "ّ": 34, "ُ": 35, "غ": 36, "ط": 37, "أ": 38, "ى": 39, "ؤ": 40, "ٌ": 41, "ث": 42, "ْ": 43, "ض": 44, "ج": 45, "ً": 46, "ظ": 47, "ش": 48, "آ": 49, "؛": 50, ":": 51, "،": 52, "(": 53, ")": 54, "؟": 55, "\"": 56, "1": 57, ".": 58, "«": 59, "»": 60, "!": 61, "?": 62, ",": 63, "-": 64, "4": 65, "×": 66, "5": 67, "7": 68, "0": 69, "*": 70, "3": 71, "8": 72, "2": 73, "_": 74, "9": 75, "6": 76}