Hugging Face's logo

WikiQuality
/
pre_filtered.yo

Fill-Mask
Transformers
Safetensors
deberta
Model card Files
xet
Community
kushaltatariya commited on
Commit
fb5b719
·
verified ·
1 Parent(s): f04606a

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +4 -7
  2. tokenization.model +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +21 -38
special_tokens_map.json CHANGED
@@ -1,9 +1,6 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "unk_token": "<unk>"
 
 
 
6
  }
tokenization.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cfbdc62f8c9a247e247364fa8a8bb7824e274935b1b2e1185ceaf111059ae8
3
+ size 310171
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +12,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[MASK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +20,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,46 +28,26 @@
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": "[BOS]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "5": {
44
- "content": "[EOS]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "[UNK]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": 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
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
+ "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
 
12
  "special": true
13
  },
14
  "1": {
15
+ "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
 
20
  "special": true
21
  },
22
  "2": {
23
+ "content": "</s>",
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
 
28
  "special": true
29
  },
30
  "3": {
31
+ "content": "<mask>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
35
  "single_word": false,
36
+ "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  },
39
+ "bos_token": "<s>",
40
+ "bos_token_id": 1,
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "</s>",
43
+ "eos_token_id": 2,
44
+ "legacy": true,
45
+ "mask_token": "<mask>",
46
+ "mask_token_id": 3,
47
  "model_max_length": 1000000000000000019884624838656,
48
+ "sp_model_kwargs": {},
49
+ "spaces_between_special_tokens": false,
50
+ "tokenizer_class": "HfSentencePieceTokenizer",
51
+ "unk_token": "<unk>",
52
+ "unk_token_id": 0
53
  }