Hugging Face's logo

aadilsayad
/
email-intent-classifier

Text Classification
Transformers
Safetensors
English
distilbert
mail
email
multi-class text classification
intent-identification
Inference Endpoints
Model card Files Community
aadilsayad commited on
Commit
a2430c7
•
1 Parent(s): 178a84b

update tokenizer files

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +3 -11
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -14
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,15 +1,7 @@
1
  {
2
- "bos_token": "[CLS]",
3
  "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": {
6
- "content": "[MASK]",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
  "sep_token": "[SEP]",
14
- "unk_token": "<unk>"
15
  }
 
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
@@ -1,22 +1,22 @@
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
10
  },
11
- "1": {
12
- "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,26 +32,24 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
- "lstrip": true,
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": true,
48
- "eos_token": "[SEP]",
49
- "keep_accents": false,
50
  "mask_token": "[MASK]",
51
  "model_max_length": 512,
52
- "pad_token": "<pad>",
53
- "remove_space": true,
54
  "sep_token": "[SEP]",
55
- "tokenizer_class": "AlbertTokenizer",
56
- "unk_token": "<unk>"
 
 
57
  }
 
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
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,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": 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