henilp105 commited on
Commit
c3a66c6
1 Parent(s): c1c8c7d

Upload tokenizer

Browse files
Files changed (2) hide show
  1. added_tokens.json +2 -2
  2. vocab.json +60 -65
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 67,
3
- "<s>": 66
4
  }
 
1
  {
2
+ "</s>": 62,
3
+ "<s>": 61
4
  }
vocab.json CHANGED
@@ -1,68 +1,63 @@
1
  {
2
- "0": 1,
3
- "2": 2,
4
- "[PAD]": 65,
5
- "[UNK]": 64,
6
  "|": 0,
7
- "": 3,
8
- "": 4,
9
- "": 5,
10
- "": 6,
11
- "": 7,
12
- "": 8,
13
- "": 9,
14
- "": 10,
15
- "": 11,
16
- "": 12,
17
- "": 13,
18
- "": 14,
19
- "": 15,
20
- "": 16,
21
- "": 17,
22
- "": 18,
23
- "": 19,
24
- "": 20,
25
- "": 21,
26
- "": 22,
27
- "": 23,
28
- "": 24,
29
- "": 25,
30
- "": 26,
31
- "": 27,
32
- "": 28,
33
- "": 29,
34
- "": 30,
35
- "": 31,
36
- "": 32,
37
- "": 33,
38
- "": 34,
39
- "": 35,
40
- "": 36,
41
- "": 37,
42
- "": 38,
43
- "": 39,
44
- "": 40,
45
- "": 41,
46
- "": 42,
47
- "": 43,
48
- "": 44,
49
- "": 45,
50
- "": 46,
51
- "": 47,
52
- "": 48,
53
- "": 49,
54
- "ి": 50,
55
- "": 51,
56
- "": 52,
57
- "": 53,
58
- "": 54,
59
- "": 55,
60
- "": 56,
61
- "": 57,
62
- "": 58,
63
- "": 59,
64
- "": 60,
65
- "్": 61,
66
- "౩": 62,
67
- "‌": 63
68
  }
 
1
  {
2
+ "[PAD]": 60,
3
+ "[UNK]": 59,
 
 
4
  "|": 0,
5
+ "": 1,
6
+ "": 2,
7
+ "": 3,
8
+ "": 4,
9
+ "": 5,
10
+ "": 6,
11
+ "": 7,
12
+ "": 8,
13
+ "": 9,
14
+ "": 10,
15
+ "": 11,
16
+ "": 12,
17
+ "": 13,
18
+ "": 14,
19
+ "": 15,
20
+ "": 16,
21
+ "": 17,
22
+ "": 18,
23
+ "": 19,
24
+ "": 20,
25
+ "": 21,
26
+ "": 22,
27
+ "": 23,
28
+ "": 24,
29
+ "": 25,
30
+ "": 26,
31
+ "": 27,
32
+ "": 28,
33
+ "": 29,
34
+ "": 30,
35
+ "": 31,
36
+ "": 32,
37
+ "": 33,
38
+ "": 34,
39
+ "": 35,
40
+ "": 36,
41
+ "": 37,
42
+ "": 38,
43
+ "": 39,
44
+ "": 40,
45
+ "": 41,
46
+ "": 42,
47
+ "": 43,
48
+ "": 44,
49
+ "": 45,
50
+ "ి": 46,
51
+ "": 47,
52
+ "": 48,
53
+ "": 49,
54
+ "": 50,
55
+ "": 51,
56
+ "": 52,
57
+ "": 53,
58
+ "": 54,
59
+ "": 55,
60
+ "": 56,
61
+ "": 57,
62
+ "": 58
 
 
 
63
  }