Hugging Face's logo

dev7halo
/
MPNet-still-training

Fill-Mask
Transformers
PyTorch
Safetensors
Korean
mpnet
Inference Endpoints
Model card Files Community
dev7halo commited on
Commit
59f1edd
·
verified ·
1 Parent(s): 226a728

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +6 -42
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +2 -60
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,25 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "[CLS]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "mask_token": {
24
  "content": "[MASK]",
25
  "lstrip": true,
@@ -27,25 +9,7 @@
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
- "pad_token": {
31
- "content": "[PAD]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "[SEP]",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "[UNK]",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "[MASK]",
7
  "lstrip": true,
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,68 +1,10 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "52000": {
44
- "content": "<s>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "52001": {
52
- "content": "</s>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- }
59
- },
60
- "bos_token": "<s>",
61
  "clean_up_tokenization_spaces": true,
62
  "cls_token": "[CLS]",
63
  "do_basic_tokenize": true,
64
  "do_lower_case": false,
65
- "eos_token": "</s>",
66
  "mask_token": "[MASK]",
67
  "model_max_length": 512,
68
  "never_split": null,
 
1
  {
2
+ "bos_token": "[CLS]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "[CLS]",
5
  "do_basic_tokenize": true,
6
  "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
  "mask_token": "[MASK]",
9
  "model_max_length": 512,
10
  "never_split": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff