Hugging Face's logo

jnsu
/
ko-math-tokenizer

Model card Files
xet
Community
jnsu commited on
Commit
b0465bb
·
1 Parent(s): 0274acc

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +2 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +6 -4
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,5 +1,7 @@
1
  {
 
2
  "cls_token": "[CLS]",
 
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
 
1
  {
2
+ "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
  "mask_token": "[MASK]",
6
  "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -41,10 +41,12 @@
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
  "do_lower_case": false,
 
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "never_split": null,
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[UNK]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_basic_tokenize": true,
48
  "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
  "mask_token": "[MASK]",
51
  "model_max_length": 512,
52
  "never_split": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff