add tokenizer

runs/Nov21_03-36-34_13e5feeb7293/events.out.tfevents.1637465813.13e5feeb7293.1750.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93212024f9763f2444832ee3ac76c83820712f7b201349dfa69d3f337eba76be
-size 4677
+oid sha256:6b66d37bbca5564643a2cd3eeb793cdeba48fb6c74ef077bfd602da012cde631
+size 15956

vocab.json

@@ -1 +1 @@
-{"u": 0, "i": 1, "y": 2, "l": 3, "d": 4, "n": 5, "g": 6, "k": 8, "'": 9, "o": 10, "e": 11, "h": 12, "c": 13, "z": 14, "f": 15, "w": 16, "a": 17, "b": 18, "v": 19, "x": 20, "m": 21, "t": 22, "j": 23, "s": 24, "r": 25, "q": 26, "p": 27, "|": 7, "[UNK]": 28, "[PAD]": 29}
+{"[PAD]": 0, "<s>": 1, "</s>": 2, "[UNK]": 3, "|": 4, "e": 5, "t": 6, "a": 7, "o": 8, "n": 9, "i": 10, "h": 11, "s": 12, "r": 13, "d": 14, "l": 15, "u": 16, "m": 17, "w": 18, "c": 19, "f": 20, "g": 21, "y": 22, "p": 23, "b": 24, "v": 25, "k": 26, "'": 27, "x": 28, "j": 29, "q": 30, "z": 31}