Upload tokenizer
Browse files- vocab.json +28 -40
vocab.json
CHANGED
@@ -1,42 +1,30 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
-
"
|
4 |
-
"[
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"d":
|
9 |
-
"e":
|
10 |
-
"f":
|
11 |
-
"g":
|
12 |
-
"h":
|
13 |
-
"i":
|
14 |
-
"j":
|
15 |
-
"k":
|
16 |
-
"l":
|
17 |
-
"m":
|
18 |
-
"n":
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"z": 1,
|
31 |
-
"|": 19,
|
32 |
-
"â": 15,
|
33 |
-
"ç": 7,
|
34 |
-
"ë": 11,
|
35 |
-
"î": 29,
|
36 |
-
"ö": 26,
|
37 |
-
"ü": 17,
|
38 |
-
"ğ": 12,
|
39 |
-
"ı": 20,
|
40 |
-
"ş": 9,
|
41 |
-
"̇": 35
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"'": 5,
|
3 |
+
":": 2,
|
4 |
+
"[PAD]": 27,
|
5 |
+
"[UNK]": 26,
|
6 |
+
"a": 9,
|
7 |
+
"b": 17,
|
8 |
+
"d": 12,
|
9 |
+
"e": 13,
|
10 |
+
"f": 1,
|
11 |
+
"g": 22,
|
12 |
+
"h": 18,
|
13 |
+
"i": 8,
|
14 |
+
"j": 10,
|
15 |
+
"k": 7,
|
16 |
+
"l": 4,
|
17 |
+
"m": 21,
|
18 |
+
"n": 3,
|
19 |
+
"p": 11,
|
20 |
+
"q": 19,
|
21 |
+
"r": 15,
|
22 |
+
"s": 0,
|
23 |
+
"t": 23,
|
24 |
+
"v": 24,
|
25 |
+
"w": 6,
|
26 |
+
"y": 14,
|
27 |
+
"z": 25,
|
28 |
+
"|": 20,
|
29 |
+
"ٱ": 16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|