Hugging Face's logo

sapadev13
/
SAPA_model

Feature Extraction
Transformers
Safetensors
bert
text-embeddings-inference
Model card Files
xet
Community
sapadev13 commited on
Commit
ae6c71a
·
verified ·
1 Parent(s): b4b468b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +9 -1
  2. tokenizer_config.json +18 -17
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
 
2
  "cls_token": "[CLS]",
 
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
7
  }
 
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
+ }
15
  }
tokenizer_config.json CHANGED
@@ -8,31 +8,31 @@
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,
@@ -41,18 +41,19 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
 
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
- "model_max_length": 512,
51
- "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "DistilBertTokenizer",
57
- "unk_token": "[UNK]"
 
58
  }
 
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
  "special": true
42
  }
43
  },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
  "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
  "extra_special_tokens": {},
50
  "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
 
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
  }