Upload tokenizer
Browse files- added_tokens.json +2 -2
- tokenizer_config.json +4 -4
- vocab.json +44 -96
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 46,
|
3 |
+
"<s>": 45
|
4 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"43": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"44": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"45": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"46": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
vocab.json
CHANGED
@@ -1,99 +1,47 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"[PAD]": 96,
|
5 |
-
"[UNK]": 95,
|
6 |
-
"_": 3,
|
7 |
-
"a": 4,
|
8 |
-
"b": 5,
|
9 |
-
"c": 6,
|
10 |
-
"d": 7,
|
11 |
-
"e": 8,
|
12 |
-
"f": 9,
|
13 |
-
"g": 10,
|
14 |
-
"h": 11,
|
15 |
-
"i": 12,
|
16 |
-
"j": 13,
|
17 |
-
"k": 14,
|
18 |
-
"l": 15,
|
19 |
-
"m": 16,
|
20 |
-
"n": 17,
|
21 |
-
"o": 18,
|
22 |
-
"p": 19,
|
23 |
-
"q": 20,
|
24 |
-
"r": 21,
|
25 |
-
"s": 22,
|
26 |
-
"t": 23,
|
27 |
-
"u": 24,
|
28 |
-
"v": 25,
|
29 |
-
"w": 26,
|
30 |
-
"x": 27,
|
31 |
-
"y": 28,
|
32 |
"|": 0,
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
72 |
-
"
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"ً": 71,
|
76 |
-
"ٌ": 72,
|
77 |
-
"ٍ": 73,
|
78 |
-
"َ": 74,
|
79 |
-
"ُ": 75,
|
80 |
-
"ِ": 76,
|
81 |
-
"ّ": 77,
|
82 |
-
"ْ": 78,
|
83 |
-
"ٰ": 79,
|
84 |
-
"چ": 80,
|
85 |
-
"ڨ": 81,
|
86 |
-
"ک": 82,
|
87 |
-
"ھ": 83,
|
88 |
-
"ی": 84,
|
89 |
-
"ۖ": 85,
|
90 |
-
"ۗ": 86,
|
91 |
-
"ۘ": 87,
|
92 |
-
"ۚ": 88,
|
93 |
-
"ۛ": 89,
|
94 |
-
"—": 90,
|
95 |
-
"…": 91,
|
96 |
-
"☭": 92,
|
97 |
-
"ﺃ": 93,
|
98 |
-
"ﻻ": 94
|
99 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 44,
|
3 |
+
"[UNK]": 43,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"|": 0,
|
5 |
+
"،": 1,
|
6 |
+
"؟": 2,
|
7 |
+
"ء": 3,
|
8 |
+
"أ": 4,
|
9 |
+
"إ": 5,
|
10 |
+
"ئ": 6,
|
11 |
+
"ا": 7,
|
12 |
+
"ب": 8,
|
13 |
+
"ة": 9,
|
14 |
+
"ت": 10,
|
15 |
+
"ج": 11,
|
16 |
+
"ح": 12,
|
17 |
+
"خ": 13,
|
18 |
+
"د": 14,
|
19 |
+
"ذ": 15,
|
20 |
+
"ر": 16,
|
21 |
+
"ز": 17,
|
22 |
+
"س": 18,
|
23 |
+
"ش": 19,
|
24 |
+
"ص": 20,
|
25 |
+
"ض": 21,
|
26 |
+
"ط": 22,
|
27 |
+
"ظ": 23,
|
28 |
+
"ع": 24,
|
29 |
+
"غ": 25,
|
30 |
+
"ف": 26,
|
31 |
+
"ق": 27,
|
32 |
+
"ك": 28,
|
33 |
+
"ل": 29,
|
34 |
+
"م": 30,
|
35 |
+
"ن": 31,
|
36 |
+
"ه": 32,
|
37 |
+
"و": 33,
|
38 |
+
"ى": 34,
|
39 |
+
"ي": 35,
|
40 |
+
"ً": 36,
|
41 |
+
"ٍ": 37,
|
42 |
+
"َ": 38,
|
43 |
+
"ُ": 39,
|
44 |
+
"ِ": 40,
|
45 |
+
"ّ": 41,
|
46 |
+
"ْ": 42
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
}
|