Hugging Face's logo

WikiQuality
/
testing_for_classification.ha

Fill-Mask
Transformers
Safetensors
deberta
Inference Endpoints
Model card Files Community
arturkulmizev commited on
Commit
5639cac
•
1 Parent(s): 35ba6a7

Upload config

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -4
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +35 -8
special_tokens_map.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
- "bos_token": "<bos>",
3
- "eos_token": "<eos>",
4
- "pad_token": "<pad>",
5
- "unk_token": "<unk>"
 
 
 
6
  }
 
1
  {
2
+ "bos_token": "[BOS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[EOS]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
  }
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": "<bos>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<eos>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<pad>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,31 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "<unk>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -33,11 +57,14 @@
33
  "special": true
34
  }
35
  },
36
- "bos_token": "<bos>",
37
  "clean_up_tokenization_spaces": true,
38
- "eos_token": "<eos>",
 
 
39
  "model_max_length": 1000000000000000019884624838656,
40
- "pad_token": "<pad>",
 
41
  "tokenizer_class": "FastTokenizerFromConfig",
42
- "unk_token": "<unk>"
43
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[MASK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[BOS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[EOS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": 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": "[PAD]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[UNK]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[CLS]",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
 
57
  "special": true
58
  }
59
  },
60
+ "bos_token": "[BOS]",
61
  "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "eos_token": "[EOS]",
64
+ "mask_token": "[MASK]",
65
  "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "[PAD]",
67
+ "sep_token": "[SEP]",
68
  "tokenizer_class": "FastTokenizerFromConfig",
69
+ "unk_token": "[UNK]"
70
  }