Hugging Face's logo

narayan214
/
distilbert-pii-before-v2

Safetensors
English
distilbert
pii-detection
ner
finance
legal
compliance
privacy
Model card Files
xet
 Community
narayan214 commited on
Commit
f79359e
·
verified ·
1 Parent(s): a360af4

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +106 -0
  2. label_mappings.json +85 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +60 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-AMOUNT",
14
+ "2": "B-COUNTRY",
15
+ "3": "B-CREDENTIALS",
16
+ "4": "B-DATE",
17
+ "5": "B-DATETIME",
18
+ "6": "B-EMAIL",
19
+ "7": "B-EXPIRYDATE",
20
+ "8": "B-FIRSTNAME",
21
+ "9": "B-IPADDRESS",
22
+ "10": "B-LASTNAME",
23
+ "11": "B-LOCATION",
24
+ "12": "B-MACADDRESS",
25
+ "13": "B-NUMBER",
26
+ "14": "B-ORGANIZATION",
27
+ "15": "B-PERCENT",
28
+ "16": "B-PHONE",
29
+ "17": "B-TIME",
30
+ "18": "B-UID",
31
+ "19": "B-ZIPCODE",
32
+ "20": "I-AMOUNT",
33
+ "21": "I-COUNTRY",
34
+ "22": "I-CREDENTIALS",
35
+ "23": "I-DATE",
36
+ "24": "I-DATETIME",
37
+ "25": "I-EMAIL",
38
+ "26": "I-EXPIRYDATE",
39
+ "27": "I-FIRSTNAME",
40
+ "28": "I-IPADDRESS",
41
+ "29": "I-LASTNAME",
42
+ "30": "I-LOCATION",
43
+ "31": "I-MACADDRESS",
44
+ "32": "I-NUMBER",
45
+ "33": "I-ORGANIZATION",
46
+ "34": "I-PERCENT",
47
+ "35": "I-PHONE",
48
+ "36": "I-TIME",
49
+ "37": "I-UID",
50
+ "38": "I-ZIPCODE"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "label2id": {
54
+ "B-AMOUNT": 1,
55
+ "B-COUNTRY": 2,
56
+ "B-CREDENTIALS": 3,
57
+ "B-DATE": 4,
58
+ "B-DATETIME": 5,
59
+ "B-EMAIL": 6,
60
+ "B-EXPIRYDATE": 7,
61
+ "B-FIRSTNAME": 8,
62
+ "B-IPADDRESS": 9,
63
+ "B-LASTNAME": 10,
64
+ "B-LOCATION": 11,
65
+ "B-MACADDRESS": 12,
66
+ "B-NUMBER": 13,
67
+ "B-ORGANIZATION": 14,
68
+ "B-PERCENT": 15,
69
+ "B-PHONE": 16,
70
+ "B-TIME": 17,
71
+ "B-UID": 18,
72
+ "B-ZIPCODE": 19,
73
+ "I-AMOUNT": 20,
74
+ "I-COUNTRY": 21,
75
+ "I-CREDENTIALS": 22,
76
+ "I-DATE": 23,
77
+ "I-DATETIME": 24,
78
+ "I-EMAIL": 25,
79
+ "I-EXPIRYDATE": 26,
80
+ "I-FIRSTNAME": 27,
81
+ "I-IPADDRESS": 28,
82
+ "I-LASTNAME": 29,
83
+ "I-LOCATION": 30,
84
+ "I-MACADDRESS": 31,
85
+ "I-NUMBER": 32,
86
+ "I-ORGANIZATION": 33,
87
+ "I-PERCENT": 34,
88
+ "I-PHONE": 35,
89
+ "I-TIME": 36,
90
+ "I-UID": 37,
91
+ "I-ZIPCODE": 38,
92
+ "O": 0
93
+ },
94
+ "max_position_embeddings": 512,
95
+ "model_type": "distilbert",
96
+ "n_heads": 12,
97
+ "n_layers": 6,
98
+ "output_past": true,
99
+ "pad_token_id": 0,
100
+ "qa_dropout": 0.1,
101
+ "seq_classif_dropout": 0.2,
102
+ "sinusoidal_pos_embds": false,
103
+ "tie_weights_": true,
104
+ "transformers_version": "4.56.1",
105
+ "vocab_size": 28996
106
+ }
label_mappings.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label2id": {
3
+ "O": 0,
4
+ "B-AMOUNT": 1,
5
+ "B-COUNTRY": 2,
6
+ "B-CREDENTIALS": 3,
7
+ "B-DATE": 4,
8
+ "B-DATETIME": 5,
9
+ "B-EMAIL": 6,
10
+ "B-EXPIRYDATE": 7,
11
+ "B-FIRSTNAME": 8,
12
+ "B-IPADDRESS": 9,
13
+ "B-LASTNAME": 10,
14
+ "B-LOCATION": 11,
15
+ "B-MACADDRESS": 12,
16
+ "B-NUMBER": 13,
17
+ "B-ORGANIZATION": 14,
18
+ "B-PERCENT": 15,
19
+ "B-PHONE": 16,
20
+ "B-TIME": 17,
21
+ "B-UID": 18,
22
+ "B-ZIPCODE": 19,
23
+ "I-AMOUNT": 20,
24
+ "I-COUNTRY": 21,
25
+ "I-CREDENTIALS": 22,
26
+ "I-DATE": 23,
27
+ "I-DATETIME": 24,
28
+ "I-EMAIL": 25,
29
+ "I-EXPIRYDATE": 26,
30
+ "I-FIRSTNAME": 27,
31
+ "I-IPADDRESS": 28,
32
+ "I-LASTNAME": 29,
33
+ "I-LOCATION": 30,
34
+ "I-MACADDRESS": 31,
35
+ "I-NUMBER": 32,
36
+ "I-ORGANIZATION": 33,
37
+ "I-PERCENT": 34,
38
+ "I-PHONE": 35,
39
+ "I-TIME": 36,
40
+ "I-UID": 37,
41
+ "I-ZIPCODE": 38
42
+ },
43
+ "id2label": {
44
+ "0": "O",
45
+ "1": "B-AMOUNT",
46
+ "2": "B-COUNTRY",
47
+ "3": "B-CREDENTIALS",
48
+ "4": "B-DATE",
49
+ "5": "B-DATETIME",
50
+ "6": "B-EMAIL",
51
+ "7": "B-EXPIRYDATE",
52
+ "8": "B-FIRSTNAME",
53
+ "9": "B-IPADDRESS",
54
+ "10": "B-LASTNAME",
55
+ "11": "B-LOCATION",
56
+ "12": "B-MACADDRESS",
57
+ "13": "B-NUMBER",
58
+ "14": "B-ORGANIZATION",
59
+ "15": "B-PERCENT",
60
+ "16": "B-PHONE",
61
+ "17": "B-TIME",
62
+ "18": "B-UID",
63
+ "19": "B-ZIPCODE",
64
+ "20": "I-AMOUNT",
65
+ "21": "I-COUNTRY",
66
+ "22": "I-CREDENTIALS",
67
+ "23": "I-DATE",
68
+ "24": "I-DATETIME",
69
+ "25": "I-EMAIL",
70
+ "26": "I-EXPIRYDATE",
71
+ "27": "I-FIRSTNAME",
72
+ "28": "I-IPADDRESS",
73
+ "29": "I-LASTNAME",
74
+ "30": "I-LOCATION",
75
+ "31": "I-MACADDRESS",
76
+ "32": "I-NUMBER",
77
+ "33": "I-ORGANIZATION",
78
+ "34": "I-PERCENT",
79
+ "35": "I-PHONE",
80
+ "36": "I-TIME",
81
+ "37": "I-UID",
82
+ "38": "I-ZIPCODE"
83
+ },
84
+ "num_labels": 39
85
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a326979a8b6b2139879e4ce8d53d1c6856227aaa183a0a11e03975158105141
3
+ size 260895956
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "stride": 0,
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "truncation_side": "right",
58
+ "truncation_strategy": "longest_first",
59
+ "unk_token": "[UNK]"
60
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607060dc1a385aeade053d5949a8e442300f240193b4ff8d5eb06938f5581f3d
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff