LH-Tech-AI commited on
Commit
a072b97
·
verified ·
1 Parent(s): 89874f1

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +146 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +16 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "ACCOUNTNAME",
17
+ "2": "ACCOUNTNUMBER",
18
+ "3": "AGE",
19
+ "4": "AMOUNT",
20
+ "5": "BIC",
21
+ "6": "BITCOINADDRESS",
22
+ "7": "BUILDINGNUMBER",
23
+ "8": "CITY",
24
+ "9": "COMPANYNAME",
25
+ "10": "COUNTY",
26
+ "11": "CREDITCARDCVV",
27
+ "12": "CREDITCARDISSUER",
28
+ "13": "CREDITCARDNUMBER",
29
+ "14": "CURRENCY",
30
+ "15": "CURRENCYCODE",
31
+ "16": "CURRENCYNAME",
32
+ "17": "CURRENCYSYMBOL",
33
+ "18": "DATE",
34
+ "19": "DOB",
35
+ "20": "EMAIL",
36
+ "21": "ETHEREUMADDRESS",
37
+ "22": "EYECOLOR",
38
+ "23": "FIRSTNAME",
39
+ "24": "GENDER",
40
+ "25": "HEIGHT",
41
+ "26": "IBAN",
42
+ "27": "IP",
43
+ "28": "IPV4",
44
+ "29": "IPV6",
45
+ "30": "JOBAREA",
46
+ "31": "JOBTITLE",
47
+ "32": "JOBTYPE",
48
+ "33": "LASTNAME",
49
+ "34": "LITECOINADDRESS",
50
+ "35": "MAC",
51
+ "36": "MASKEDNUMBER",
52
+ "37": "MIDDLENAME",
53
+ "38": "NEARBYGPSCOORDINATE",
54
+ "39": "ORDINALDIRECTION",
55
+ "40": "PASSWORD",
56
+ "41": "PHONEIMEI",
57
+ "42": "PHONENUMBER",
58
+ "43": "PIN",
59
+ "44": "PREFIX",
60
+ "45": "SECONDARYADDRESS",
61
+ "46": "SEX",
62
+ "47": "SSN",
63
+ "48": "STATE",
64
+ "49": "STREET",
65
+ "50": "TIME",
66
+ "51": "URL",
67
+ "52": "USERAGENT",
68
+ "53": "USERNAME",
69
+ "54": "VEHICLEVIN",
70
+ "55": "VEHICLEVRM",
71
+ "56": "ZIPCODE"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "is_decoder": false,
76
+ "label2id": {
77
+ "ACCOUNTNAME": 1,
78
+ "ACCOUNTNUMBER": 2,
79
+ "AGE": 3,
80
+ "AMOUNT": 4,
81
+ "BIC": 5,
82
+ "BITCOINADDRESS": 6,
83
+ "BUILDINGNUMBER": 7,
84
+ "CITY": 8,
85
+ "COMPANYNAME": 9,
86
+ "COUNTY": 10,
87
+ "CREDITCARDCVV": 11,
88
+ "CREDITCARDISSUER": 12,
89
+ "CREDITCARDNUMBER": 13,
90
+ "CURRENCY": 14,
91
+ "CURRENCYCODE": 15,
92
+ "CURRENCYNAME": 16,
93
+ "CURRENCYSYMBOL": 17,
94
+ "DATE": 18,
95
+ "DOB": 19,
96
+ "EMAIL": 20,
97
+ "ETHEREUMADDRESS": 21,
98
+ "EYECOLOR": 22,
99
+ "FIRSTNAME": 23,
100
+ "GENDER": 24,
101
+ "HEIGHT": 25,
102
+ "IBAN": 26,
103
+ "IP": 27,
104
+ "IPV4": 28,
105
+ "IPV6": 29,
106
+ "JOBAREA": 30,
107
+ "JOBTITLE": 31,
108
+ "JOBTYPE": 32,
109
+ "LASTNAME": 33,
110
+ "LITECOINADDRESS": 34,
111
+ "MAC": 35,
112
+ "MASKEDNUMBER": 36,
113
+ "MIDDLENAME": 37,
114
+ "NEARBYGPSCOORDINATE": 38,
115
+ "O": 0,
116
+ "ORDINALDIRECTION": 39,
117
+ "PASSWORD": 40,
118
+ "PHONEIMEI": 41,
119
+ "PHONENUMBER": 42,
120
+ "PIN": 43,
121
+ "PREFIX": 44,
122
+ "SECONDARYADDRESS": 45,
123
+ "SEX": 46,
124
+ "SSN": 47,
125
+ "STATE": 48,
126
+ "STREET": 49,
127
+ "TIME": 50,
128
+ "URL": 51,
129
+ "USERAGENT": 52,
130
+ "USERNAME": 53,
131
+ "VEHICLEVIN": 54,
132
+ "VEHICLEVRM": 55,
133
+ "ZIPCODE": 56
134
+ },
135
+ "layer_norm_eps": 1e-05,
136
+ "max_position_embeddings": 514,
137
+ "model_type": "roberta",
138
+ "num_attention_heads": 12,
139
+ "num_hidden_layers": 6,
140
+ "pad_token_id": 1,
141
+ "tie_word_embeddings": true,
142
+ "transformers_version": "5.0.0",
143
+ "type_vocab_size": 1,
144
+ "use_cache": false,
145
+ "vocab_size": 50265
146
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1464cd83000177df0248108c59eca30b23dc8de23366feb05d55d5e827de83f7
3
+ size 5137