Hugging Face's logo

yanshaoshow
/
cc_domain_classifier

Transformers
PyTorch
deberta-v2
Model card Files Community
1
yanshaoshow commited on
Commit
b5486b9
·
1 Parent(s): bcfe16b

first commit

Browse files
Files changed (7) hide show
  1. added_tokens.json +3 -0
  2. config.json +63 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +15 -0
  5. spm.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +58 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "microsoft/deberta-v3-base",
3
+ "model_type": "deberta-v2",
4
+ "config_path": null,
5
+ "fc_dropout": 0.2,
6
+ "id2label": {
7
+ "0": "Adult",
8
+ "1": "Arts_and_Entertainment",
9
+ "10": "Health",
10
+ "11": "Hobbies_and_Leisure",
11
+ "12": "Home_and_Garden",
12
+ "13": "Internet_and_Telecom",
13
+ "14": "Jobs_and_Education",
14
+ "15": "Law_and_Government",
15
+ "16": "News",
16
+ "17": "Online_Communities",
17
+ "18": "People_and_Society",
18
+ "19": "Pets_and_Animals",
19
+ "2": "Autos_and_Vehicles",
20
+ "20": "Real_Estate",
21
+ "21": "Science",
22
+ "22": "Sensitive_Subjects",
23
+ "23": "Shopping",
24
+ "24": "Sports",
25
+ "25": "Travel_and_Transportation",
26
+ "3": "Beauty_and_Fitness",
27
+ "4": "Books_and_Literature",
28
+ "5": "Business_and_Industrial",
29
+ "6": "Computers_and_Electronics",
30
+ "7": "Finance",
31
+ "8": "Food_and_Drink",
32
+ "9": "Games"
33
+ },
34
+ "label2id": {
35
+ "Adult": 0,
36
+ "Arts_and_Entertainment": 1,
37
+ "Autos_and_Vehicles": 2,
38
+ "Beauty_and_Fitness": 3,
39
+ "Books_and_Literature": 4,
40
+ "Business_and_Industrial": 5,
41
+ "Computers_and_Electronics": 6,
42
+ "Finance": 7,
43
+ "Food_and_Drink": 8,
44
+ "Games": 9,
45
+ "Health": 10,
46
+ "Hobbies_and_Leisure": 11,
47
+ "Home_and_Garden": 12,
48
+ "Internet_and_Telecom": 13,
49
+ "Jobs_and_Education": 14,
50
+ "Law_and_Government": 15,
51
+ "News": 16,
52
+ "Online_Communities": 17,
53
+ "People_and_Society": 18,
54
+ "Pets_and_Animals": 19,
55
+ "Real_Estate": 20,
56
+ "Science": 21,
57
+ "Sensitive_Subjects": 22,
58
+ "Shopping": 23,
59
+ "Sports": 24,
60
+ "Travel_and_Transportation": 25
61
+ },
62
+ "pretrained": true
63
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ad552a3ddc6228efcf45df7b42ad214547a9b7afb98548c6a65515c074ab94
3
+ size 735487530
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[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,
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": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
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
+ }