samuelchiji commited on
Commit
5a50225
1 Parent(s): 8c195ca

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +21 -22
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 34,
3
- "<s>": 33
4
  }
 
1
  {
2
+ "</s>": 33,
3
+ "<s>": 32
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "31": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "32": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "33": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "34": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "30": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "31": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "32": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "33": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,35 +1,34 @@
1
  {
2
- "2": 18,
3
- "[PAD]": 32,
4
- "[UNK]": 31,
5
- "a": 28,
6
  "b": 1,
7
- "c": 30,
8
- "d": 17,
9
  "e": 8,
10
- "f": 20,
11
- "g": 22,
12
  "h": 9,
13
  "i": 0,
14
  "j": 4,
15
- "k": 14,
16
- "l": 13,
17
  "m": 3,
18
- "n": 16,
19
  "o": 7,
20
- "p": 12,
21
- "q": 29,
22
  "r": 6,
23
- "s": 27,
24
- "t": 21,
25
  "u": 10,
26
- "v": 23,
27
- "w": 24,
28
- "x": 26,
29
- "y": 25,
30
- "z": 15,
31
  "|": 5,
32
- "ẹ": 19,
33
- "—": 11,
34
  "’": 2
35
  }
 
1
  {
2
+ "2": 17,
3
+ "[PAD]": 31,
4
+ "[UNK]": 30,
5
+ "a": 27,
6
  "b": 1,
7
+ "c": 29,
8
+ "d": 16,
9
  "e": 8,
10
+ "f": 19,
11
+ "g": 21,
12
  "h": 9,
13
  "i": 0,
14
  "j": 4,
15
+ "k": 13,
16
+ "l": 12,
17
  "m": 3,
18
+ "n": 15,
19
  "o": 7,
20
+ "p": 11,
21
+ "q": 28,
22
  "r": 6,
23
+ "s": 26,
24
+ "t": 20,
25
  "u": 10,
26
+ "v": 22,
27
+ "w": 23,
28
+ "x": 25,
29
+ "y": 24,
30
+ "z": 14,
31
  "|": 5,
32
+ "ẹ": 18,
 
33
  "’": 2
34
  }