add tokenizer

runs/Dec08_14-26-57_116e510e5c72/events.out.tfevents.1638973683.116e510e5c72.108.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896e7d7ceebf91706d3a95cb7c0c68b22b72da54c88bd77ff27edd829e7e88e3
-size 4682
+oid sha256:1162923939168e326f6d6a669a785802c46848089b94b2881eca57e8f3379bb4
+size 7057

vocab.json

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