Hugging Face's logo

depgh4311
/
io_mail_classifier

Transformers
TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
depgh4311 commited on
Commit
6329737
·
verified ·
1 Parent(s): 1bb657c

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +51 -15
  2. tokenizer_config.json +89 -57
special_tokens_map.json CHANGED
@@ -1,15 +1,51 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
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": "</s>",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
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": false,
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": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
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
+ }
tokenizer_config.json CHANGED
@@ -1,57 +1,89 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 512,
52
- "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": "<unk>"
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "id2label": {
51
+ "0": "C1",
52
+ "1": "C13",
53
+ "2": "C17",
54
+ "3": "C22",
55
+ "4": "C28",
56
+ "5": "C33",
57
+ "6": "C38",
58
+ "7": "C46",
59
+ "8": "C52",
60
+ "9": "C7"
61
+ },
62
+ "label2id": {
63
+ "C1": 0,
64
+ "C13": 1,
65
+ "C17": 2,
66
+ "C22": 3,
67
+ "C28": 4,
68
+ "C33": 5,
69
+ "C38": 6,
70
+ "C46": 7,
71
+ "C52": 8,
72
+ "C7": 9
73
+ },
74
+ "mask_token": "<mask>",
75
+ "max_length": 512,
76
+ "model_max_length": 512,
77
+ "num_labels": 10,
78
+ "pad_to_multiple_of": null,
79
+ "pad_token": "<pad>",
80
+ "pad_token_type_id": 0,
81
+ "padding_side": "right",
82
+ "sep_token": "</s>",
83
+ "stride": 0,
84
+ "tokenizer_class": "RobertaTokenizer",
85
+ "trim_offsets": true,
86
+ "truncation_side": "right",
87
+ "truncation_strategy": "longest_first",
88
+ "unk_token": "<unk>"
89
+ }