Hugging Face's logo

Spaces:
vuminhtue
/
NER_PII_Bert_Multilingual
Sleeping

App Files Community
vuminhtue commited on
Commit
a30897f
·
verified ·
1 Parent(s): bafee35

Upload 7 files

Browse files
Files changed (6) hide show
  1. Bert_NER_PII_Multilingual/config.json +113 -0
  2. Bert_NER_PII_Multilingual/special_tokens_map.json +7 -0
  3. Bert_NER_PII_Multilingual/tokenizer.json +0 -0
  4. Bert_NER_PII_Multilingual/tokenizer_config.json +55 -0
  5. Bert_NER_PII_Multilingual/training_args.bin +3 -0
  6. Bert_NER_PII_Multilingual/vocab.txt +0 -0
Bert_NER_PII_Multilingual/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "ACCOUNTNAME",
14
+ "1": "IBAN",
15
+ "2": "COINADDRESS",
16
+ "3": "ADDRESS",
17
+ "4": "AGE",
18
+ "5": "BIC",
19
+ "6": "CREDITCARDISSUER",
20
+ "7": "CREDITCARDNUMBER",
21
+ "8": "CURRENCY",
22
+ "9": "DATE",
23
+ "10": "EMAIL",
24
+ "11": "COLOR",
25
+ "12": "GENDER",
26
+ "13": "GEO",
27
+ "14": "HEIGHT",
28
+ "15": "JOB",
29
+ "16": "MAC",
30
+ "17": "MISC",
31
+ "18": "USERNAME",
32
+ "19": "NAME",
33
+ "20": "NEARBYGPSCOORDINATE",
34
+ "21": "ORDINALDIRECTION",
35
+ "22": "ORG",
36
+ "23": "PASSWORD",
37
+ "24": "PHONEIMEI",
38
+ "25": "PHONENUMBER",
39
+ "26": "PREFIX",
40
+ "27": "SSN",
41
+ "28": "STREET",
42
+ "29": "TIME",
43
+ "30": "URL",
44
+ "31": "VEHICLEVIN",
45
+ "32": "VEHICLEVRM",
46
+ "33": "ZIPCODE",
47
+ "34": "IP",
48
+ "35": "NUM",
49
+ "36": "BLOODTYPE",
50
+ "37": "WEIGHTS",
51
+ "38": "O"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 3072,
55
+ "label2id": {
56
+ "ACCOUNTNAME": 0,
57
+ "ADDRESS": 3,
58
+ "AGE": 4,
59
+ "BIC": 5,
60
+ "BLOODTYPE": 36,
61
+ "COINADDRESS": 2,
62
+ "COLOR": 11,
63
+ "CREDITCARDISSUER": 6,
64
+ "CREDITCARDNUMBER": 7,
65
+ "CURRENCY": 8,
66
+ "DATE": 9,
67
+ "EMAIL": 10,
68
+ "GENDER": 12,
69
+ "GEO": 13,
70
+ "HEIGHT": 14,
71
+ "IBAN": 1,
72
+ "IP": 34,
73
+ "JOB": 15,
74
+ "MAC": 16,
75
+ "MISC": 17,
76
+ "NAME": 19,
77
+ "NEARBYGPSCOORDINATE": 20,
78
+ "NUM": 35,
79
+ "O": 38,
80
+ "ORDINALDIRECTION": 21,
81
+ "ORG": 22,
82
+ "PASSWORD": 23,
83
+ "PHONEIMEI": 24,
84
+ "PHONENUMBER": 25,
85
+ "PREFIX": 26,
86
+ "SSN": 27,
87
+ "STREET": 28,
88
+ "TIME": 29,
89
+ "URL": 30,
90
+ "USERNAME": 18,
91
+ "VEHICLEVIN": 31,
92
+ "VEHICLEVRM": 32,
93
+ "WEIGHTS": 37,
94
+ "ZIPCODE": 33
95
+ },
96
+ "layer_norm_eps": 1e-12,
97
+ "max_position_embeddings": 512,
98
+ "model_type": "bert",
99
+ "num_attention_heads": 12,
100
+ "num_hidden_layers": 12,
101
+ "pad_token_id": 0,
102
+ "pooler_fc_size": 768,
103
+ "pooler_num_attention_heads": 12,
104
+ "pooler_num_fc_layers": 3,
105
+ "pooler_size_per_head": 128,
106
+ "pooler_type": "first_token_transform",
107
+ "position_embedding_type": "absolute",
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.41.0.dev0",
110
+ "type_vocab_size": 2,
111
+ "use_cache": true,
112
+ "vocab_size": 105879
113
+ }
Bert_NER_PII_Multilingual/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
Bert_NER_PII_Multilingual/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Bert_NER_PII_Multilingual/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
Bert_NER_PII_Multilingual/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993c363874b4ea5f56ddf2edeea7560482f719a5e32c24f24b1c5d1b4815de9f
3
+ size 129
Bert_NER_PII_Multilingual/vocab.txt ADDED
The diff for this file is too large to render. See raw diff