July24 commited on
Commit
5d95cb9
·
verified ·
1 Parent(s): 006d204

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -49
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +14 -17
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
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": false,
26
- "normalized": false,
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": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,31 +8,31 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
- "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
- "content": "[UNK]",
29
  "lstrip": false,
30
- "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128000": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -41,18 +41,15 @@
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
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
 
55
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff