Upload tokenizer
Browse files- added_tokens.json +2 -2
- vocab.json +17 -20
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 35,
|
3 |
+
"<s>": 34
|
4 |
}
|
vocab.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"tur": {
|
3 |
-
"[PAD]":
|
4 |
-
"[UNK]":
|
5 |
"a": 1,
|
6 |
"b": 2,
|
7 |
"c": 3,
|
@@ -18,24 +18,21 @@
|
|
18 |
"n": 14,
|
19 |
"o": 15,
|
20 |
"p": 16,
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"y": 25,
|
30 |
-
"z": 26,
|
31 |
"|": 0,
|
32 |
-
"ç":
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"̇": 34
|
40 |
}
|
41 |
}
|
|
|
1 |
{
|
2 |
"tur": {
|
3 |
+
"[PAD]": 33,
|
4 |
+
"[UNK]": 32,
|
5 |
"a": 1,
|
6 |
"b": 2,
|
7 |
"c": 3,
|
|
|
18 |
"n": 14,
|
19 |
"o": 15,
|
20 |
"p": 16,
|
21 |
+
"r": 17,
|
22 |
+
"s": 18,
|
23 |
+
"t": 19,
|
24 |
+
"u": 20,
|
25 |
+
"v": 21,
|
26 |
+
"w": 22,
|
27 |
+
"y": 23,
|
28 |
+
"z": 24,
|
|
|
|
|
29 |
"|": 0,
|
30 |
+
"ç": 25,
|
31 |
+
"ö": 26,
|
32 |
+
"ü": 27,
|
33 |
+
"ğ": 28,
|
34 |
+
"ı": 29,
|
35 |
+
"ş": 30,
|
36 |
+
"̇": 31
|
|
|
37 |
}
|
38 |
}
|