PuxAI commited on
Commit
8546d41
·
verified ·
1 Parent(s): 6bf2431

Auto-upload CRF fine-tuned google-bert-bert-base-multilingual-cased-CRF

Browse files
google-bert-bert-base-multilingual-cased-CRF/classification_report.txt ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ ACCOUNTNAME 0.96 0.99 0.98 242
4
+ ACCOUNTNUMBER 1.00 0.99 0.99 266
5
+ AGE 0.95 0.97 0.96 847
6
+ AMOUNT 0.91 0.97 0.94 309
7
+ BIC 0.98 0.98 0.98 63
8
+ BITCOINADDRESS 0.97 1.00 0.98 161
9
+ BUILDINGNUMBER 0.98 0.98 0.98 1471
10
+ CITY 0.97 0.99 0.98 1723
11
+ COMPANYNAME 0.98 1.00 0.99 251
12
+ COUNTY 0.98 0.99 0.98 221
13
+ CREDITCARDCVV 0.97 0.96 0.97 73
14
+ CREDITCARDISSUER 0.99 1.00 0.99 135
15
+ CREDITCARDNUMBER 0.92 0.98 0.95 365
16
+ DATE 0.95 0.98 0.96 1606
17
+ DOB 0.78 0.75 0.76 245
18
+ DRIVERLICENSENUM 0.96 0.79 0.87 264
19
+ EMAIL 1.00 1.00 1.00 1583
20
+ ETHEREUMADDRESS 1.00 1.00 1.00 102
21
+ EYECOLOR 0.99 0.99 0.99 73
22
+ FIRSTNAME 0.93 0.94 0.94 9837
23
+ GENDER 0.99 1.00 1.00 1011
24
+ HEIGHT 0.99 1.00 0.99 67
25
+ IBAN 1.00 1.00 1.00 188
26
+ IPADDRESS 1.00 1.00 1.00 549
27
+ JOBAREA 0.97 0.98 0.97 237
28
+ JOBTYPE 0.98 0.99 0.98 208
29
+ LASTNAME 0.89 0.86 0.87 4002
30
+ LITECOINADDRESS 0.96 0.89 0.93 57
31
+ MASKEDNUMBER 0.97 0.90 0.93 250
32
+ MIDDLENAME 0.81 0.92 0.86 275
33
+ NEARBYGPSCOORDINATE 1.00 1.00 1.00 212
34
+ ORDINALDIRECTION 0.97 0.96 0.96 93
35
+ PASSPORTNUM 0.89 0.98 0.93 355
36
+ PASSWORD 0.99 1.00 0.99 201
37
+ PHONEIMEI 0.99 0.99 0.99 187
38
+ PHONENUMBER 1.00 1.00 1.00 1704
39
+ PIN 0.93 0.92 0.93 74
40
+ PREFIX 0.97 0.99 0.98 1453
41
+ SECONDARYADDRESS 0.98 1.00 0.99 272
42
+ SSN/CCCD 0.93 0.95 0.94 1167
43
+ STATE 0.96 0.98 0.97 224
44
+ STREET 0.99 0.99 0.99 1576
45
+ TAXNUM 0.94 0.92 0.93 284
46
+ TIME 0.99 1.00 1.00 2131
47
+ URL 1.00 1.00 1.00 330
48
+ USERAGENT 0.99 1.00 1.00 151
49
+ USERNAME 0.98 0.99 0.99 259
50
+ VEHICLEVIN 1.00 1.00 1.00 70
51
+ VEHICLEVRM 0.96 1.00 0.98 71
52
+ ZIPCODE 0.96 0.98 0.97 579
53
+
54
+ micro avg 0.95 0.96 0.95 38074
55
+ macro avg 0.96 0.97 0.97 38074
56
+ weighted avg 0.95 0.96 0.95 38074
google-bert-bert-base-multilingual-cased-CRF/config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "CRFTokenClassifier"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-ACCOUNTNAME",
18
+ "2": "I-ACCOUNTNAME",
19
+ "3": "B-ACCOUNTNUMBER",
20
+ "4": "I-ACCOUNTNUMBER",
21
+ "5": "B-AGE",
22
+ "6": "I-AGE",
23
+ "7": "B-AMOUNT",
24
+ "8": "I-AMOUNT",
25
+ "9": "B-BIC",
26
+ "10": "I-BIC",
27
+ "11": "B-BITCOINADDRESS",
28
+ "12": "I-BITCOINADDRESS",
29
+ "13": "B-BUILDINGNUMBER",
30
+ "14": "I-BUILDINGNUMBER",
31
+ "15": "B-CITY",
32
+ "16": "I-CITY",
33
+ "17": "B-COMPANYNAME",
34
+ "18": "I-COMPANYNAME",
35
+ "19": "B-COUNTY",
36
+ "20": "I-COUNTY",
37
+ "21": "B-CREDITCARDCVV",
38
+ "22": "I-CREDITCARDCVV",
39
+ "23": "B-CREDITCARDISSUER",
40
+ "24": "I-CREDITCARDISSUER",
41
+ "25": "B-CREDITCARDNUMBER",
42
+ "26": "I-CREDITCARDNUMBER",
43
+ "27": "B-DATE",
44
+ "28": "I-DATE",
45
+ "29": "B-DOB",
46
+ "30": "I-DOB",
47
+ "31": "B-DRIVERLICENSENUM",
48
+ "32": "I-DRIVERLICENSENUM",
49
+ "33": "B-EMAIL",
50
+ "34": "I-EMAIL",
51
+ "35": "B-ETHEREUMADDRESS",
52
+ "36": "I-ETHEREUMADDRESS",
53
+ "37": "B-EYECOLOR",
54
+ "38": "I-EYECOLOR",
55
+ "39": "B-FIRSTNAME",
56
+ "40": "I-FIRSTNAME",
57
+ "41": "B-GENDER",
58
+ "42": "I-GENDER",
59
+ "43": "B-HEIGHT",
60
+ "44": "I-HEIGHT",
61
+ "45": "B-IBAN",
62
+ "46": "I-IBAN",
63
+ "47": "B-IPADDRESS",
64
+ "48": "I-IPADDRESS",
65
+ "49": "B-JOBAREA",
66
+ "50": "I-JOBAREA",
67
+ "51": "B-JOBTYPE",
68
+ "52": "I-JOBTYPE",
69
+ "53": "B-LASTNAME",
70
+ "54": "I-LASTNAME",
71
+ "55": "B-LITECOINADDRESS",
72
+ "56": "I-LITECOINADDRESS",
73
+ "57": "B-MASKEDNUMBER",
74
+ "58": "I-MASKEDNUMBER",
75
+ "59": "B-MIDDLENAME",
76
+ "60": "I-MIDDLENAME",
77
+ "61": "B-NEARBYGPSCOORDINATE",
78
+ "62": "I-NEARBYGPSCOORDINATE",
79
+ "63": "B-ORDINALDIRECTION",
80
+ "64": "I-ORDINALDIRECTION",
81
+ "65": "B-PASSPORTNUM",
82
+ "66": "I-PASSPORTNUM",
83
+ "67": "B-PASSWORD",
84
+ "68": "I-PASSWORD",
85
+ "69": "B-PHONEIMEI",
86
+ "70": "I-PHONEIMEI",
87
+ "71": "B-PHONENUMBER",
88
+ "72": "I-PHONENUMBER",
89
+ "73": "B-PIN",
90
+ "74": "I-PIN",
91
+ "75": "B-PREFIX",
92
+ "76": "I-PREFIX",
93
+ "77": "B-SECONDARYADDRESS",
94
+ "78": "I-SECONDARYADDRESS",
95
+ "79": "B-SSN/CCCD",
96
+ "80": "I-SSN/CCCD",
97
+ "81": "B-STATE",
98
+ "82": "I-STATE",
99
+ "83": "B-STREET",
100
+ "84": "I-STREET",
101
+ "85": "B-TAXNUM",
102
+ "86": "I-TAXNUM",
103
+ "87": "B-TIME",
104
+ "88": "I-TIME",
105
+ "89": "B-URL",
106
+ "90": "I-URL",
107
+ "91": "B-USERAGENT",
108
+ "92": "I-USERAGENT",
109
+ "93": "B-USERNAME",
110
+ "94": "I-USERNAME",
111
+ "95": "B-VEHICLEVIN",
112
+ "96": "I-VEHICLEVIN",
113
+ "97": "B-VEHICLEVRM",
114
+ "98": "I-VEHICLEVRM",
115
+ "99": "B-ZIPCODE",
116
+ "100": "I-ZIPCODE"
117
+ },
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3072,
120
+ "is_decoder": false,
121
+ "label2id": {
122
+ "B-ACCOUNTNAME": 1,
123
+ "B-ACCOUNTNUMBER": 3,
124
+ "B-AGE": 5,
125
+ "B-AMOUNT": 7,
126
+ "B-BIC": 9,
127
+ "B-BITCOINADDRESS": 11,
128
+ "B-BUILDINGNUMBER": 13,
129
+ "B-CITY": 15,
130
+ "B-COMPANYNAME": 17,
131
+ "B-COUNTY": 19,
132
+ "B-CREDITCARDCVV": 21,
133
+ "B-CREDITCARDISSUER": 23,
134
+ "B-CREDITCARDNUMBER": 25,
135
+ "B-DATE": 27,
136
+ "B-DOB": 29,
137
+ "B-DRIVERLICENSENUM": 31,
138
+ "B-EMAIL": 33,
139
+ "B-ETHEREUMADDRESS": 35,
140
+ "B-EYECOLOR": 37,
141
+ "B-FIRSTNAME": 39,
142
+ "B-GENDER": 41,
143
+ "B-HEIGHT": 43,
144
+ "B-IBAN": 45,
145
+ "B-IPADDRESS": 47,
146
+ "B-JOBAREA": 49,
147
+ "B-JOBTYPE": 51,
148
+ "B-LASTNAME": 53,
149
+ "B-LITECOINADDRESS": 55,
150
+ "B-MASKEDNUMBER": 57,
151
+ "B-MIDDLENAME": 59,
152
+ "B-NEARBYGPSCOORDINATE": 61,
153
+ "B-ORDINALDIRECTION": 63,
154
+ "B-PASSPORTNUM": 65,
155
+ "B-PASSWORD": 67,
156
+ "B-PHONEIMEI": 69,
157
+ "B-PHONENUMBER": 71,
158
+ "B-PIN": 73,
159
+ "B-PREFIX": 75,
160
+ "B-SECONDARYADDRESS": 77,
161
+ "B-SSN/CCCD": 79,
162
+ "B-STATE": 81,
163
+ "B-STREET": 83,
164
+ "B-TAXNUM": 85,
165
+ "B-TIME": 87,
166
+ "B-URL": 89,
167
+ "B-USERAGENT": 91,
168
+ "B-USERNAME": 93,
169
+ "B-VEHICLEVIN": 95,
170
+ "B-VEHICLEVRM": 97,
171
+ "B-ZIPCODE": 99,
172
+ "I-ACCOUNTNAME": 2,
173
+ "I-ACCOUNTNUMBER": 4,
174
+ "I-AGE": 6,
175
+ "I-AMOUNT": 8,
176
+ "I-BIC": 10,
177
+ "I-BITCOINADDRESS": 12,
178
+ "I-BUILDINGNUMBER": 14,
179
+ "I-CITY": 16,
180
+ "I-COMPANYNAME": 18,
181
+ "I-COUNTY": 20,
182
+ "I-CREDITCARDCVV": 22,
183
+ "I-CREDITCARDISSUER": 24,
184
+ "I-CREDITCARDNUMBER": 26,
185
+ "I-DATE": 28,
186
+ "I-DOB": 30,
187
+ "I-DRIVERLICENSENUM": 32,
188
+ "I-EMAIL": 34,
189
+ "I-ETHEREUMADDRESS": 36,
190
+ "I-EYECOLOR": 38,
191
+ "I-FIRSTNAME": 40,
192
+ "I-GENDER": 42,
193
+ "I-HEIGHT": 44,
194
+ "I-IBAN": 46,
195
+ "I-IPADDRESS": 48,
196
+ "I-JOBAREA": 50,
197
+ "I-JOBTYPE": 52,
198
+ "I-LASTNAME": 54,
199
+ "I-LITECOINADDRESS": 56,
200
+ "I-MASKEDNUMBER": 58,
201
+ "I-MIDDLENAME": 60,
202
+ "I-NEARBYGPSCOORDINATE": 62,
203
+ "I-ORDINALDIRECTION": 64,
204
+ "I-PASSPORTNUM": 66,
205
+ "I-PASSWORD": 68,
206
+ "I-PHONEIMEI": 70,
207
+ "I-PHONENUMBER": 72,
208
+ "I-PIN": 74,
209
+ "I-PREFIX": 76,
210
+ "I-SECONDARYADDRESS": 78,
211
+ "I-SSN/CCCD": 80,
212
+ "I-STATE": 82,
213
+ "I-STREET": 84,
214
+ "I-TAXNUM": 86,
215
+ "I-TIME": 88,
216
+ "I-URL": 90,
217
+ "I-USERAGENT": 92,
218
+ "I-USERNAME": 94,
219
+ "I-VEHICLEVIN": 96,
220
+ "I-VEHICLEVRM": 98,
221
+ "I-ZIPCODE": 100,
222
+ "O": 0
223
+ },
224
+ "layer_norm_eps": 1e-12,
225
+ "max_position_embeddings": 512,
226
+ "model_type": "bert",
227
+ "num_attention_heads": 12,
228
+ "num_hidden_layers": 12,
229
+ "pad_token_id": 0,
230
+ "pooler_fc_size": 768,
231
+ "pooler_num_attention_heads": 12,
232
+ "pooler_num_fc_layers": 3,
233
+ "pooler_size_per_head": 128,
234
+ "pooler_type": "first_token_transform",
235
+ "tie_word_embeddings": true,
236
+ "transformers_version": "5.3.0",
237
+ "type_vocab_size": 2,
238
+ "use_cache": false,
239
+ "vocab_size": 119547
240
+ }
google-bert-bert-base-multilingual-cased-CRF/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75b6458fd69ca5bb727692b30adb32d7ab8fc324a6238b329cfa24a20d94250
3
+ size 711853203
google-bert-bert-base-multilingual-cased-CRF/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
google-bert-bert-base-multilingual-cased-CRF/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }