PuxAI commited on
Commit
7dd0bbc
·
verified ·
1 Parent(s): 057d132

Upload folder using huggingface_hub

Browse files
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/config.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "TransformerCrfForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ACCOUNT_NUMBER",
15
+ "2": "I-ACCOUNT_NUMBER",
16
+ "3": "B-AGE",
17
+ "4": "I-AGE",
18
+ "5": "B-API_KEY",
19
+ "6": "I-API_KEY",
20
+ "7": "B-BANK_ROUTING_NUMBER",
21
+ "8": "I-BANK_ROUTING_NUMBER",
22
+ "9": "B-BIOMETRIC_IDENTIFIER",
23
+ "10": "I-BIOMETRIC_IDENTIFIER",
24
+ "11": "B-BLOOD_TYPE",
25
+ "12": "I-BLOOD_TYPE",
26
+ "13": "B-CERTIFICATE_LICENSE_NUMBER",
27
+ "14": "I-CERTIFICATE_LICENSE_NUMBER",
28
+ "15": "B-CITY",
29
+ "16": "I-CITY",
30
+ "17": "B-COMPANY_NAME",
31
+ "18": "I-COMPANY_NAME",
32
+ "19": "B-COORDINATE",
33
+ "20": "I-COORDINATE",
34
+ "21": "B-COUNTRY",
35
+ "22": "I-COUNTRY",
36
+ "23": "B-COUNTY",
37
+ "24": "I-COUNTY",
38
+ "25": "B-CREDIT_DEBIT_CARD",
39
+ "26": "I-CREDIT_DEBIT_CARD",
40
+ "27": "B-CUSTOMER_ID",
41
+ "28": "I-CUSTOMER_ID",
42
+ "29": "B-CVV",
43
+ "30": "I-CVV",
44
+ "31": "B-DATE",
45
+ "32": "I-DATE",
46
+ "33": "B-DATE_OF_BIRTH",
47
+ "34": "I-DATE_OF_BIRTH",
48
+ "35": "B-DATE_TIME",
49
+ "36": "I-DATE_TIME",
50
+ "37": "B-DEVICE_IDENTIFIER",
51
+ "38": "I-DEVICE_IDENTIFIER",
52
+ "39": "B-EDUCATION_LEVEL",
53
+ "40": "I-EDUCATION_LEVEL",
54
+ "41": "B-EMAIL",
55
+ "42": "I-EMAIL",
56
+ "43": "B-EMPLOYEE_ID",
57
+ "44": "I-EMPLOYEE_ID",
58
+ "45": "B-EMPLOYMENT_STATUS",
59
+ "46": "I-EMPLOYMENT_STATUS",
60
+ "47": "B-FAX_NUMBER",
61
+ "48": "I-FAX_NUMBER",
62
+ "49": "B-FIRST_NAME",
63
+ "50": "I-FIRST_NAME",
64
+ "51": "B-GENDER",
65
+ "52": "I-GENDER",
66
+ "53": "B-HEALTH_PLAN_BENEFICIARY_NUMBER",
67
+ "54": "I-HEALTH_PLAN_BENEFICIARY_NUMBER",
68
+ "55": "B-HTTP_COOKIE",
69
+ "56": "I-HTTP_COOKIE",
70
+ "57": "B-IPV4",
71
+ "58": "I-IPV4",
72
+ "59": "B-IPV6",
73
+ "60": "I-IPV6",
74
+ "61": "B-LANGUAGE",
75
+ "62": "I-LANGUAGE",
76
+ "63": "B-LAST_NAME",
77
+ "64": "I-LAST_NAME",
78
+ "65": "B-LICENSE_PLATE",
79
+ "66": "I-LICENSE_PLATE",
80
+ "67": "B-MAC_ADDRESS",
81
+ "68": "I-MAC_ADDRESS",
82
+ "69": "B-MEDICAL_RECORD_NUMBER",
83
+ "70": "I-MEDICAL_RECORD_NUMBER",
84
+ "71": "B-NATIONAL_ID",
85
+ "72": "I-NATIONAL_ID",
86
+ "73": "B-OCCUPATION",
87
+ "74": "I-OCCUPATION",
88
+ "75": "B-PASSWORD",
89
+ "76": "I-PASSWORD",
90
+ "77": "B-PHONE_NUMBER",
91
+ "78": "I-PHONE_NUMBER",
92
+ "79": "B-PIN",
93
+ "80": "I-PIN",
94
+ "81": "B-POLITICAL_VIEW",
95
+ "82": "I-POLITICAL_VIEW",
96
+ "83": "B-POSTCODE",
97
+ "84": "I-POSTCODE",
98
+ "85": "B-RACE_ETHNICITY",
99
+ "86": "I-RACE_ETHNICITY",
100
+ "87": "B-RELIGIOUS_BELIEF",
101
+ "88": "I-RELIGIOUS_BELIEF",
102
+ "89": "B-SEXUALITY",
103
+ "90": "I-SEXUALITY",
104
+ "91": "B-SSN",
105
+ "92": "I-SSN",
106
+ "93": "B-STATE",
107
+ "94": "I-STATE",
108
+ "95": "B-STREET_ADDRESS",
109
+ "96": "I-STREET_ADDRESS",
110
+ "97": "B-SWIFT_BIC",
111
+ "98": "I-SWIFT_BIC",
112
+ "99": "B-TAX_ID",
113
+ "100": "I-TAX_ID",
114
+ "101": "B-TIME",
115
+ "102": "I-TIME",
116
+ "103": "B-UNIQUE_ID",
117
+ "104": "I-UNIQUE_ID",
118
+ "105": "B-URL",
119
+ "106": "I-URL",
120
+ "107": "B-USER_NAME",
121
+ "108": "I-USER_NAME",
122
+ "109": "B-VEHICLE_IDENTIFIER",
123
+ "110": "I-VEHICLE_IDENTIFIER"
124
+ },
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 3072,
127
+ "label2id": {
128
+ "B-ACCOUNT_NUMBER": 1,
129
+ "B-AGE": 3,
130
+ "B-API_KEY": 5,
131
+ "B-BANK_ROUTING_NUMBER": 7,
132
+ "B-BIOMETRIC_IDENTIFIER": 9,
133
+ "B-BLOOD_TYPE": 11,
134
+ "B-CERTIFICATE_LICENSE_NUMBER": 13,
135
+ "B-CITY": 15,
136
+ "B-COMPANY_NAME": 17,
137
+ "B-COORDINATE": 19,
138
+ "B-COUNTRY": 21,
139
+ "B-COUNTY": 23,
140
+ "B-CREDIT_DEBIT_CARD": 25,
141
+ "B-CUSTOMER_ID": 27,
142
+ "B-CVV": 29,
143
+ "B-DATE": 31,
144
+ "B-DATE_OF_BIRTH": 33,
145
+ "B-DATE_TIME": 35,
146
+ "B-DEVICE_IDENTIFIER": 37,
147
+ "B-EDUCATION_LEVEL": 39,
148
+ "B-EMAIL": 41,
149
+ "B-EMPLOYEE_ID": 43,
150
+ "B-EMPLOYMENT_STATUS": 45,
151
+ "B-FAX_NUMBER": 47,
152
+ "B-FIRST_NAME": 49,
153
+ "B-GENDER": 51,
154
+ "B-HEALTH_PLAN_BENEFICIARY_NUMBER": 53,
155
+ "B-HTTP_COOKIE": 55,
156
+ "B-IPV4": 57,
157
+ "B-IPV6": 59,
158
+ "B-LANGUAGE": 61,
159
+ "B-LAST_NAME": 63,
160
+ "B-LICENSE_PLATE": 65,
161
+ "B-MAC_ADDRESS": 67,
162
+ "B-MEDICAL_RECORD_NUMBER": 69,
163
+ "B-NATIONAL_ID": 71,
164
+ "B-OCCUPATION": 73,
165
+ "B-PASSWORD": 75,
166
+ "B-PHONE_NUMBER": 77,
167
+ "B-PIN": 79,
168
+ "B-POLITICAL_VIEW": 81,
169
+ "B-POSTCODE": 83,
170
+ "B-RACE_ETHNICITY": 85,
171
+ "B-RELIGIOUS_BELIEF": 87,
172
+ "B-SEXUALITY": 89,
173
+ "B-SSN": 91,
174
+ "B-STATE": 93,
175
+ "B-STREET_ADDRESS": 95,
176
+ "B-SWIFT_BIC": 97,
177
+ "B-TAX_ID": 99,
178
+ "B-TIME": 101,
179
+ "B-UNIQUE_ID": 103,
180
+ "B-URL": 105,
181
+ "B-USER_NAME": 107,
182
+ "B-VEHICLE_IDENTIFIER": 109,
183
+ "I-ACCOUNT_NUMBER": 2,
184
+ "I-AGE": 4,
185
+ "I-API_KEY": 6,
186
+ "I-BANK_ROUTING_NUMBER": 8,
187
+ "I-BIOMETRIC_IDENTIFIER": 10,
188
+ "I-BLOOD_TYPE": 12,
189
+ "I-CERTIFICATE_LICENSE_NUMBER": 14,
190
+ "I-CITY": 16,
191
+ "I-COMPANY_NAME": 18,
192
+ "I-COORDINATE": 20,
193
+ "I-COUNTRY": 22,
194
+ "I-COUNTY": 24,
195
+ "I-CREDIT_DEBIT_CARD": 26,
196
+ "I-CUSTOMER_ID": 28,
197
+ "I-CVV": 30,
198
+ "I-DATE": 32,
199
+ "I-DATE_OF_BIRTH": 34,
200
+ "I-DATE_TIME": 36,
201
+ "I-DEVICE_IDENTIFIER": 38,
202
+ "I-EDUCATION_LEVEL": 40,
203
+ "I-EMAIL": 42,
204
+ "I-EMPLOYEE_ID": 44,
205
+ "I-EMPLOYMENT_STATUS": 46,
206
+ "I-FAX_NUMBER": 48,
207
+ "I-FIRST_NAME": 50,
208
+ "I-GENDER": 52,
209
+ "I-HEALTH_PLAN_BENEFICIARY_NUMBER": 54,
210
+ "I-HTTP_COOKIE": 56,
211
+ "I-IPV4": 58,
212
+ "I-IPV6": 60,
213
+ "I-LANGUAGE": 62,
214
+ "I-LAST_NAME": 64,
215
+ "I-LICENSE_PLATE": 66,
216
+ "I-MAC_ADDRESS": 68,
217
+ "I-MEDICAL_RECORD_NUMBER": 70,
218
+ "I-NATIONAL_ID": 72,
219
+ "I-OCCUPATION": 74,
220
+ "I-PASSWORD": 76,
221
+ "I-PHONE_NUMBER": 78,
222
+ "I-PIN": 80,
223
+ "I-POLITICAL_VIEW": 82,
224
+ "I-POSTCODE": 84,
225
+ "I-RACE_ETHNICITY": 86,
226
+ "I-RELIGIOUS_BELIEF": 88,
227
+ "I-SEXUALITY": 90,
228
+ "I-SSN": 92,
229
+ "I-STATE": 94,
230
+ "I-STREET_ADDRESS": 96,
231
+ "I-SWIFT_BIC": 98,
232
+ "I-TAX_ID": 100,
233
+ "I-TIME": 102,
234
+ "I-UNIQUE_ID": 104,
235
+ "I-URL": 106,
236
+ "I-USER_NAME": 108,
237
+ "I-VEHICLE_IDENTIFIER": 110,
238
+ "O": 0
239
+ },
240
+ "layer_norm_eps": 1e-12,
241
+ "max_position_embeddings": 512,
242
+ "model_type": "bert",
243
+ "num_attention_heads": 12,
244
+ "num_hidden_layers": 12,
245
+ "pad_token_id": 0,
246
+ "pooler_fc_size": 768,
247
+ "pooler_num_attention_heads": 12,
248
+ "pooler_num_fc_layers": 3,
249
+ "pooler_size_per_head": 128,
250
+ "pooler_type": "first_token_transform",
251
+ "position_embedding_type": "absolute",
252
+ "transformers_version": "4.57.6",
253
+ "type_vocab_size": 2,
254
+ "use_cache": true,
255
+ "vocab_size": 119547
256
+ }
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904339a017c63b20d7488fbfe5e7e50abe43d8deaa3910ccf03d1dfa92421294
3
+ size 711830552
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/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
+ }
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec20844a052f10a8c7bee67d5925f139ff70e30e6e3246d48df6aaa86a26e81
3
+ size 5905
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/training_meta.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "token_based",
3
+ "base_model": "google-bert/bert-base-multilingual-cased",
4
+ "tagging_scheme": "bio",
5
+ "use_crf": true,
6
+ "dataset": "nemotron-pii-ready",
7
+ "label_list": [
8
+ "O",
9
+ "B-ACCOUNT_NUMBER",
10
+ "I-ACCOUNT_NUMBER",
11
+ "B-AGE",
12
+ "I-AGE",
13
+ "B-API_KEY",
14
+ "I-API_KEY",
15
+ "B-BANK_ROUTING_NUMBER",
16
+ "I-BANK_ROUTING_NUMBER",
17
+ "B-BIOMETRIC_IDENTIFIER",
18
+ "I-BIOMETRIC_IDENTIFIER",
19
+ "B-BLOOD_TYPE",
20
+ "I-BLOOD_TYPE",
21
+ "B-CERTIFICATE_LICENSE_NUMBER",
22
+ "I-CERTIFICATE_LICENSE_NUMBER",
23
+ "B-CITY",
24
+ "I-CITY",
25
+ "B-COMPANY_NAME",
26
+ "I-COMPANY_NAME",
27
+ "B-COORDINATE",
28
+ "I-COORDINATE",
29
+ "B-COUNTRY",
30
+ "I-COUNTRY",
31
+ "B-COUNTY",
32
+ "I-COUNTY",
33
+ "B-CREDIT_DEBIT_CARD",
34
+ "I-CREDIT_DEBIT_CARD",
35
+ "B-CUSTOMER_ID",
36
+ "I-CUSTOMER_ID",
37
+ "B-CVV",
38
+ "I-CVV",
39
+ "B-DATE",
40
+ "I-DATE",
41
+ "B-DATE_OF_BIRTH",
42
+ "I-DATE_OF_BIRTH",
43
+ "B-DATE_TIME",
44
+ "I-DATE_TIME",
45
+ "B-DEVICE_IDENTIFIER",
46
+ "I-DEVICE_IDENTIFIER",
47
+ "B-EDUCATION_LEVEL",
48
+ "I-EDUCATION_LEVEL",
49
+ "B-EMAIL",
50
+ "I-EMAIL",
51
+ "B-EMPLOYEE_ID",
52
+ "I-EMPLOYEE_ID",
53
+ "B-EMPLOYMENT_STATUS",
54
+ "I-EMPLOYMENT_STATUS",
55
+ "B-FAX_NUMBER",
56
+ "I-FAX_NUMBER",
57
+ "B-FIRST_NAME",
58
+ "I-FIRST_NAME",
59
+ "B-GENDER",
60
+ "I-GENDER",
61
+ "B-HEALTH_PLAN_BENEFICIARY_NUMBER",
62
+ "I-HEALTH_PLAN_BENEFICIARY_NUMBER",
63
+ "B-HTTP_COOKIE",
64
+ "I-HTTP_COOKIE",
65
+ "B-IPV4",
66
+ "I-IPV4",
67
+ "B-IPV6",
68
+ "I-IPV6",
69
+ "B-LANGUAGE",
70
+ "I-LANGUAGE",
71
+ "B-LAST_NAME",
72
+ "I-LAST_NAME",
73
+ "B-LICENSE_PLATE",
74
+ "I-LICENSE_PLATE",
75
+ "B-MAC_ADDRESS",
76
+ "I-MAC_ADDRESS",
77
+ "B-MEDICAL_RECORD_NUMBER",
78
+ "I-MEDICAL_RECORD_NUMBER",
79
+ "B-NATIONAL_ID",
80
+ "I-NATIONAL_ID",
81
+ "B-OCCUPATION",
82
+ "I-OCCUPATION",
83
+ "B-PASSWORD",
84
+ "I-PASSWORD",
85
+ "B-PHONE_NUMBER",
86
+ "I-PHONE_NUMBER",
87
+ "B-PIN",
88
+ "I-PIN",
89
+ "B-POLITICAL_VIEW",
90
+ "I-POLITICAL_VIEW",
91
+ "B-POSTCODE",
92
+ "I-POSTCODE",
93
+ "B-RACE_ETHNICITY",
94
+ "I-RACE_ETHNICITY",
95
+ "B-RELIGIOUS_BELIEF",
96
+ "I-RELIGIOUS_BELIEF",
97
+ "B-SEXUALITY",
98
+ "I-SEXUALITY",
99
+ "B-SSN",
100
+ "I-SSN",
101
+ "B-STATE",
102
+ "I-STATE",
103
+ "B-STREET_ADDRESS",
104
+ "I-STREET_ADDRESS",
105
+ "B-SWIFT_BIC",
106
+ "I-SWIFT_BIC",
107
+ "B-TAX_ID",
108
+ "I-TAX_ID",
109
+ "B-TIME",
110
+ "I-TIME",
111
+ "B-UNIQUE_ID",
112
+ "I-UNIQUE_ID",
113
+ "B-URL",
114
+ "I-URL",
115
+ "B-USER_NAME",
116
+ "I-USER_NAME",
117
+ "B-VEHICLE_IDENTIFIER",
118
+ "I-VEHICLE_IDENTIFIER"
119
+ ],
120
+ "max_seq_length": 512,
121
+ "timestamp": "2026-04-06T05:20:22.822614"
122
+ }
nemotron-pii-ready/bert-crf-bio-bert-base-multilingual-cased/vocab.txt ADDED
The diff for this file is too large to render. See raw diff