add tokenizer

vocab.json

@@ -1 +1 @@
-{"p": 0, "i": 1, "r": 2, "x": 3, "s": 4, "g": 5, "v": 6, "c": 7, "a": 8, "j": 9, "f": 10, "b": 11, "w": 12, "n": 13, "l": 15, "o": 16, "z": 18, "q": 19, "e": 20, "t": 21, "k": 22, "y": 23, "m": 24, "h": 25, "d": 26, "u": 27, "[UNK]": 28, "[PAD]": 29, "|": 14}
+{"e": 0, "t": 1, "q": 2, "d": 3, "w": 4, "l": 5, "x": 6, "k": 7, "m": 8, "o": 9, "s": 11, "f": 12, "z": 13, "b": 14, "p": 15, "n": 16, "i": 17, "y": 18, "j": 20, "v": 21, "a": 22, "c": 23, "g": 24, "u": 25, "h": 26, "r": 27, "[UNK]": 28, "[PAD]": 29, "|": 10}