Upload tokenizer
Browse files- vocab.json +46 -46
vocab.json
CHANGED
|
@@ -1,50 +1,50 @@
|
|
| 1 |
{
|
| 2 |
-
"!":
|
| 3 |
-
"'":
|
| 4 |
-
"(":
|
| 5 |
-
")":
|
| 6 |
-
"-":
|
| 7 |
-
".":
|
| 8 |
-
"/":
|
| 9 |
-
"0":
|
| 10 |
-
"1":
|
| 11 |
-
"2":
|
| 12 |
-
"3":
|
| 13 |
-
"4":
|
| 14 |
-
"5":
|
| 15 |
-
"6":
|
| 16 |
-
"7":
|
| 17 |
-
"8":
|
| 18 |
-
"9":
|
| 19 |
"[PAD]": 47,
|
| 20 |
"[UNK]": 46,
|
| 21 |
-
"a":
|
| 22 |
-
"b":
|
| 23 |
-
"c":
|
| 24 |
-
"d":
|
| 25 |
-
"e":
|
| 26 |
-
"f":
|
| 27 |
-
"g":
|
| 28 |
-
"h":
|
| 29 |
-
"i":
|
| 30 |
-
"j":
|
| 31 |
-
"k":
|
| 32 |
-
"l":
|
| 33 |
-
"m":
|
| 34 |
-
"n":
|
| 35 |
-
"o":
|
| 36 |
-
"p":
|
| 37 |
-
"q":
|
| 38 |
-
"r":
|
| 39 |
-
"s":
|
| 40 |
-
"t":
|
| 41 |
-
"u":
|
| 42 |
-
"v":
|
| 43 |
-
"w":
|
| 44 |
-
"x":
|
| 45 |
-
"y":
|
| 46 |
-
"z":
|
| 47 |
-
"|":
|
| 48 |
-
"ː":
|
| 49 |
-
"’":
|
| 50 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"!": 18,
|
| 3 |
+
"'": 20,
|
| 4 |
+
"(": 41,
|
| 5 |
+
")": 4,
|
| 6 |
+
"-": 17,
|
| 7 |
+
".": 25,
|
| 8 |
+
"/": 43,
|
| 9 |
+
"0": 16,
|
| 10 |
+
"1": 5,
|
| 11 |
+
"2": 24,
|
| 12 |
+
"3": 22,
|
| 13 |
+
"4": 45,
|
| 14 |
+
"5": 29,
|
| 15 |
+
"6": 12,
|
| 16 |
+
"7": 14,
|
| 17 |
+
"8": 23,
|
| 18 |
+
"9": 32,
|
| 19 |
"[PAD]": 47,
|
| 20 |
"[UNK]": 46,
|
| 21 |
+
"a": 21,
|
| 22 |
+
"b": 30,
|
| 23 |
+
"c": 19,
|
| 24 |
+
"d": 37,
|
| 25 |
+
"e": 6,
|
| 26 |
+
"f": 15,
|
| 27 |
+
"g": 44,
|
| 28 |
+
"h": 9,
|
| 29 |
+
"i": 34,
|
| 30 |
+
"j": 11,
|
| 31 |
+
"k": 31,
|
| 32 |
+
"l": 38,
|
| 33 |
+
"m": 28,
|
| 34 |
+
"n": 7,
|
| 35 |
+
"o": 26,
|
| 36 |
+
"p": 42,
|
| 37 |
+
"q": 36,
|
| 38 |
+
"r": 2,
|
| 39 |
+
"s": 3,
|
| 40 |
+
"t": 1,
|
| 41 |
+
"u": 13,
|
| 42 |
+
"v": 0,
|
| 43 |
+
"w": 27,
|
| 44 |
+
"x": 39,
|
| 45 |
+
"y": 33,
|
| 46 |
+
"z": 35,
|
| 47 |
+
"|": 10,
|
| 48 |
+
"ː": 8,
|
| 49 |
+
"’": 40
|
| 50 |
}
|