kkahadze commited on
Commit
b9c40eb
·
verified ·
1 Parent(s): 6880d07

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +15 -17
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 49,
3
- "<s>": 48
4
  }
 
1
  {
2
+ "</s>": 47,
3
+ "<s>": 46
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "46": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "47": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "48": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "49": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "44": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "45": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "46": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "47": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 47,
3
- "[UNK]": 46,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
@@ -32,19 +32,17 @@
32
  "ħ": 28,
33
  "ŏ": 29,
34
  "š": 30,
35
- "ŭ": 31,
36
- "ž": 32,
37
- "ǧ": 33,
38
- "ǯ": 34,
39
- "ǰ": 35,
40
- "ɣ": 36,
41
- "ɬ": 37,
42
- "ʒ": 38,
43
- "ʔ": 39,
44
- "ʕ": 40,
45
- "ʡ": 41,
46
- "ʲ": 42,
47
- "ʷ": 43,
48
- "ː": 44,
49
- "ⁿ": 45
50
  }
 
1
  {
2
+ "[PAD]": 45,
3
+ "[UNK]": 44,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
 
32
  "ħ": 28,
33
  "ŏ": 29,
34
  "š": 30,
35
+ "ž": 31,
36
+ "ǧ": 32,
37
+ "ǰ": 33,
38
+ "ɣ": 34,
39
+ "ɬ": 35,
40
+ "ʒ": 36,
41
+ "ʔ": 37,
42
+ "ʕ": 38,
43
+ "ʡ": 39,
44
+ "ʲ": 40,
45
+ "ʷ": 41,
46
+ "ː": 42,
47
+ "": 43
 
 
48
  }