add tokenizer

vocab.json

@@ -1 +1 @@
-{"x": 0, "r": 1, "b": 2, "y": 3, "i": 4, "z": 5, "s": 6, "e": 7, "l": 8, "g": 9, "k": 10, "d": 11, "m": 12, "p": 13, "c": 14, "w": 15, "f": 16, "u": 18, "'": 19, "v": 20, "h": 21, "a": 22, "q": 23, "o": 24, "j": 25, "t": 26, "n": 27, "|": 17, "[UNK]": 28, "[PAD]": 29}
+{"l": 0, "i": 1, "u": 2, "o": 3, "n": 4, "p": 5, "m": 6, "k": 7, "c": 8, "e": 9, "r": 10, "v": 11, "g": 12, "q": 13, "d": 14, "t": 15, "w": 16, "a": 17, "'": 18, "f": 19, "j": 20, "h": 21, "z": 22, "b": 23, "s": 24, "y": 25, "x": 27, "|": 26, "[UNK]": 28, "[PAD]": 29}