add tokenizer
Browse files- added_tokens.json +2 -2
- vocab.json +15 -44
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 18,
|
3 |
+
"<s>": 17
|
4 |
}
|
vocab.json
CHANGED
@@ -1,48 +1,19 @@
|
|
1 |
{
|
2 |
-
"[PAD]":
|
3 |
-
"[UNK]":
|
4 |
"|": 0,
|
5 |
-
"ء": 1,
|
6 |
"ا": 2,
|
7 |
-
"ب":
|
8 |
-
"ت":
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"ض": 16,
|
21 |
-
"ط": 17,
|
22 |
-
"ظ": 18,
|
23 |
-
"ع": 19,
|
24 |
-
"غ": 20,
|
25 |
-
"ف": 21,
|
26 |
-
"ق": 22,
|
27 |
-
"ل": 23,
|
28 |
-
"م": 24,
|
29 |
-
"ن": 25,
|
30 |
-
"و": 26,
|
31 |
-
"ى": 27,
|
32 |
-
"ي": 28,
|
33 |
-
"ً": 29,
|
34 |
-
"ٓ": 30,
|
35 |
-
"ٹ": 31,
|
36 |
-
"پ": 32,
|
37 |
-
"چ": 33,
|
38 |
-
"ڈ": 34,
|
39 |
-
"ڑ": 35,
|
40 |
-
"ژ": 36,
|
41 |
-
"ک": 37,
|
42 |
-
"گ": 38,
|
43 |
-
"ں": 39,
|
44 |
-
"ھ": 40,
|
45 |
-
"ہ": 41,
|
46 |
-
"ی": 42,
|
47 |
-
"ے": 43
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 16,
|
3 |
+
"[UNK]": 15,
|
4 |
"|": 0,
|
|
|
5 |
"ا": 2,
|
6 |
+
"ب": 14,
|
7 |
+
"ت": 13,
|
8 |
+
"د": 1,
|
9 |
+
"ز": 7,
|
10 |
+
"س": 9,
|
11 |
+
"ل": 11,
|
12 |
+
"م": 12,
|
13 |
+
"ڑ": 8,
|
14 |
+
"ک": 5,
|
15 |
+
"ھ": 6,
|
16 |
+
"ہ": 4,
|
17 |
+
"ی": 3,
|
18 |
+
"ے": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|