Hugging Face's logo

Gaykar
/
PhishingDistilBERT

Safetensors
English
distilbert
Model card Files
xet
Community
Gaykar commited on
Commit
1f1a3eb
·
verified ·
1 Parent(s): 16683dc

Upload 7 files

Browse files

This will be used for generating text features.

Files changed (7) hide show
  1. added_tokens.json +8 -0
  2. config.json +24 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +112 -0
  7. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[EBODY]": 30525,
3
+ "[ESUB]": 30523,
4
+ "[LINK]": 30526,
5
+ "[PHONE]": 30527,
6
+ "[SBODY]": 30524,
7
+ "[SSUB]": 30522
8
+ }
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "transformers_version": "4.57.1",
23
+ "vocab_size": 30528
24
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd96fe1fd5b635475346066d1ba6cf58365810bff1b49162f4a0db00513ee4f
3
+ size 267850992
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[SSUB]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[ESUB]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[SBODY]",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "[EBODY]",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "[LINK]",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "[PHONE]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "cls_token": "[CLS]",
47
+ "mask_token": "[MASK]",
48
+ "pad_token": "[PAD]",
49
+ "sep_token": "[SEP]",
50
+ "unk_token": "[UNK]"
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
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,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "[SSUB]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "[ESUB]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "30524": {
60
+ "content": "[SBODY]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "30525": {
68
+ "content": "[EBODY]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "30526": {
76
+ "content": "[LINK]",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "30527": {
84
+ "content": "[PHONE]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ }
91
+ },
92
+ "additional_special_tokens": [
93
+ "[SSUB]",
94
+ "[ESUB]",
95
+ "[SBODY]",
96
+ "[EBODY]",
97
+ "[LINK]",
98
+ "[PHONE]"
99
+ ],
100
+ "clean_up_tokenization_spaces": false,
101
+ "cls_token": "[CLS]",
102
+ "do_lower_case": true,
103
+ "extra_special_tokens": {},
104
+ "mask_token": "[MASK]",
105
+ "model_max_length": 512,
106
+ "pad_token": "[PAD]",
107
+ "sep_token": "[SEP]",
108
+ "strip_accents": null,
109
+ "tokenize_chinese_chars": true,
110
+ "tokenizer_class": "DistilBertTokenizer",
111
+ "unk_token": "[UNK]"
112
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff