Hugging Face's logo

juanquivilla
/
deberta-base-en-wiki

Fill-Mask
Transformers
Safetensors
deberta
Generated from Trainer
Inference Endpoints
Model card Files Community
juanquivilla commited on
Commit
5055f5c
•
1 Parent(s): f3a6171

Upload tokenizer

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