Hugging Face's logo

kabir5297
/
DebertaPII

Token Classification
Transformers
Safetensors
deberta
Inference Endpoints
Model card Files Community
kabir5297 commited on
Commit
eeac8ec
•
1 Parent(s): 5a70616

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +42 -6
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +13 -11
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,10 +1,46 @@
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]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "unk_token": {
9
  "content": "[UNK]",
10
  "lstrip": false,
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
  "unk_token": {
45
  "content": "[UNK]",
46
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,9 +1,11 @@
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
@@ -11,7 +13,7 @@
11
  "1": {
12
  "content": "[CLS]",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,7 +21,7 @@
19
  "2": {
20
  "content": "[SEP]",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -32,27 +34,27 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128000": {
36
  "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_lower_case": false,
48
  "eos_token": "[SEP]",
 
49
  "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
- "sp_model_kwargs": {},
54
- "split_by_punct": false,
55
- "tokenizer_class": "DebertaV2Tokenizer",
56
  "unk_token": "[UNK]",
57
- "vocab_type": "spm"
58
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": true,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "[PAD]",
7
  "lstrip": false,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
13
  "1": {
14
  "content": "[CLS]",
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
 
21
  "2": {
22
  "content": "[SEP]",
23
  "lstrip": false,
24
+ "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "50264": {
38
  "content": "[MASK]",
39
+ "lstrip": true,
40
+ "normalized": true,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  }
45
  },
46
+ "additional_special_tokens": [],
47
  "bos_token": "[CLS]",
48
  "clean_up_tokenization_spaces": true,
49
  "cls_token": "[CLS]",
50
  "do_lower_case": false,
51
  "eos_token": "[SEP]",
52
+ "errors": "replace",
53
  "mask_token": "[MASK]",
54
+ "model_max_length": 512,
55
  "pad_token": "[PAD]",
56
  "sep_token": "[SEP]",
57
+ "tokenizer_class": "DebertaTokenizer",
 
 
58
  "unk_token": "[UNK]",
59
+ "vocab_type": "gpt2"
60
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff