quynong commited on
Commit
b5693b4
·
verified ·
1 Parent(s): fdf2add

Upload folder using huggingface_hub

Browse files
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/config.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForTokenClassification"
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-ACCOUNT_ID",
18
+ "2": "I-ACCOUNT_ID",
19
+ "3": "B-ADDRESS",
20
+ "4": "I-ADDRESS",
21
+ "5": "B-AGE",
22
+ "6": "I-AGE",
23
+ "7": "B-API_KEY",
24
+ "8": "I-API_KEY",
25
+ "9": "B-BANK_ACCOUNT",
26
+ "10": "I-BANK_ACCOUNT",
27
+ "11": "B-BANK_NAME",
28
+ "12": "I-BANK_NAME",
29
+ "13": "B-BIRTHDATE",
30
+ "14": "I-BIRTHDATE",
31
+ "15": "B-CARD_ISSUER",
32
+ "16": "I-CARD_ISSUER",
33
+ "17": "B-CARD_NUMBER",
34
+ "18": "I-CARD_NUMBER",
35
+ "19": "B-COORDINATE",
36
+ "20": "I-COORDINATE",
37
+ "21": "B-CVV",
38
+ "22": "I-CVV",
39
+ "23": "B-DATE",
40
+ "24": "I-DATE",
41
+ "25": "B-EMAIL",
42
+ "26": "I-EMAIL",
43
+ "27": "B-EMPLOYEE_ID",
44
+ "28": "I-EMPLOYEE_ID",
45
+ "29": "B-ETHNICITY",
46
+ "30": "I-ETHNICITY",
47
+ "31": "B-GENDER",
48
+ "32": "I-GENDER",
49
+ "33": "B-IBAN",
50
+ "34": "I-IBAN",
51
+ "35": "B-INSURANCE_ID",
52
+ "36": "I-INSURANCE_ID",
53
+ "37": "B-IP",
54
+ "38": "I-IP",
55
+ "39": "B-IP_ADDRESS",
56
+ "40": "I-IP_ADDRESS",
57
+ "41": "B-JOB_TITLE",
58
+ "42": "I-JOB_TITLE",
59
+ "43": "B-LICENSE",
60
+ "44": "I-LICENSE",
61
+ "45": "B-LOCATION",
62
+ "46": "I-LOCATION",
63
+ "47": "B-MARITAL",
64
+ "48": "I-MARITAL",
65
+ "49": "B-MEDICAL_INFO",
66
+ "50": "I-MEDICAL_INFO",
67
+ "51": "B-MONEY",
68
+ "52": "I-MONEY",
69
+ "53": "B-NATIONALITY",
70
+ "54": "I-NATIONALITY",
71
+ "55": "B-NATIONAL_ID",
72
+ "56": "I-NATIONAL_ID",
73
+ "57": "B-ORGANIZATION",
74
+ "58": "I-ORGANIZATION",
75
+ "59": "B-PASSPORT",
76
+ "60": "I-PASSPORT",
77
+ "61": "B-PASSPORT_NUM",
78
+ "62": "I-PASSPORT_NUM",
79
+ "63": "B-PASSWORD",
80
+ "64": "I-PASSWORD",
81
+ "65": "B-PERSON",
82
+ "66": "I-PERSON",
83
+ "67": "B-PHONE",
84
+ "68": "I-PHONE",
85
+ "69": "B-PIN",
86
+ "70": "I-PIN",
87
+ "71": "B-PLATE",
88
+ "72": "I-PLATE",
89
+ "73": "B-PREFIX",
90
+ "74": "I-PREFIX",
91
+ "75": "B-RELIGION",
92
+ "76": "I-RELIGION",
93
+ "77": "B-STUDENT_ID",
94
+ "78": "I-STUDENT_ID",
95
+ "79": "B-SWIFT",
96
+ "80": "I-SWIFT",
97
+ "81": "B-TICKET_ID",
98
+ "82": "I-TICKET_ID",
99
+ "83": "B-TIME",
100
+ "84": "I-TIME",
101
+ "85": "B-TIN",
102
+ "86": "I-TIN",
103
+ "87": "B-TRADE_UNION",
104
+ "88": "I-TRADE_UNION",
105
+ "89": "B-URL",
106
+ "90": "I-URL",
107
+ "91": "B-USERNAME",
108
+ "92": "I-USERNAME",
109
+ "93": "B-WALLET",
110
+ "94": "I-WALLET",
111
+ "95": "B-ZIP_CODE",
112
+ "96": "I-ZIP_CODE"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 3072,
116
+ "is_decoder": false,
117
+ "label2id": {
118
+ "B-ACCOUNT_ID": 1,
119
+ "B-ADDRESS": 3,
120
+ "B-AGE": 5,
121
+ "B-API_KEY": 7,
122
+ "B-BANK_ACCOUNT": 9,
123
+ "B-BANK_NAME": 11,
124
+ "B-BIRTHDATE": 13,
125
+ "B-CARD_ISSUER": 15,
126
+ "B-CARD_NUMBER": 17,
127
+ "B-COORDINATE": 19,
128
+ "B-CVV": 21,
129
+ "B-DATE": 23,
130
+ "B-EMAIL": 25,
131
+ "B-EMPLOYEE_ID": 27,
132
+ "B-ETHNICITY": 29,
133
+ "B-GENDER": 31,
134
+ "B-IBAN": 33,
135
+ "B-INSURANCE_ID": 35,
136
+ "B-IP": 37,
137
+ "B-IP_ADDRESS": 39,
138
+ "B-JOB_TITLE": 41,
139
+ "B-LICENSE": 43,
140
+ "B-LOCATION": 45,
141
+ "B-MARITAL": 47,
142
+ "B-MEDICAL_INFO": 49,
143
+ "B-MONEY": 51,
144
+ "B-NATIONALITY": 53,
145
+ "B-NATIONAL_ID": 55,
146
+ "B-ORGANIZATION": 57,
147
+ "B-PASSPORT": 59,
148
+ "B-PASSPORT_NUM": 61,
149
+ "B-PASSWORD": 63,
150
+ "B-PERSON": 65,
151
+ "B-PHONE": 67,
152
+ "B-PIN": 69,
153
+ "B-PLATE": 71,
154
+ "B-PREFIX": 73,
155
+ "B-RELIGION": 75,
156
+ "B-STUDENT_ID": 77,
157
+ "B-SWIFT": 79,
158
+ "B-TICKET_ID": 81,
159
+ "B-TIME": 83,
160
+ "B-TIN": 85,
161
+ "B-TRADE_UNION": 87,
162
+ "B-URL": 89,
163
+ "B-USERNAME": 91,
164
+ "B-WALLET": 93,
165
+ "B-ZIP_CODE": 95,
166
+ "I-ACCOUNT_ID": 2,
167
+ "I-ADDRESS": 4,
168
+ "I-AGE": 6,
169
+ "I-API_KEY": 8,
170
+ "I-BANK_ACCOUNT": 10,
171
+ "I-BANK_NAME": 12,
172
+ "I-BIRTHDATE": 14,
173
+ "I-CARD_ISSUER": 16,
174
+ "I-CARD_NUMBER": 18,
175
+ "I-COORDINATE": 20,
176
+ "I-CVV": 22,
177
+ "I-DATE": 24,
178
+ "I-EMAIL": 26,
179
+ "I-EMPLOYEE_ID": 28,
180
+ "I-ETHNICITY": 30,
181
+ "I-GENDER": 32,
182
+ "I-IBAN": 34,
183
+ "I-INSURANCE_ID": 36,
184
+ "I-IP": 38,
185
+ "I-IP_ADDRESS": 40,
186
+ "I-JOB_TITLE": 42,
187
+ "I-LICENSE": 44,
188
+ "I-LOCATION": 46,
189
+ "I-MARITAL": 48,
190
+ "I-MEDICAL_INFO": 50,
191
+ "I-MONEY": 52,
192
+ "I-NATIONALITY": 54,
193
+ "I-NATIONAL_ID": 56,
194
+ "I-ORGANIZATION": 58,
195
+ "I-PASSPORT": 60,
196
+ "I-PASSPORT_NUM": 62,
197
+ "I-PASSWORD": 64,
198
+ "I-PERSON": 66,
199
+ "I-PHONE": 68,
200
+ "I-PIN": 70,
201
+ "I-PLATE": 72,
202
+ "I-PREFIX": 74,
203
+ "I-RELIGION": 76,
204
+ "I-STUDENT_ID": 78,
205
+ "I-SWIFT": 80,
206
+ "I-TICKET_ID": 82,
207
+ "I-TIME": 84,
208
+ "I-TIN": 86,
209
+ "I-TRADE_UNION": 88,
210
+ "I-URL": 90,
211
+ "I-USERNAME": 92,
212
+ "I-WALLET": 94,
213
+ "I-ZIP_CODE": 96,
214
+ "O": 0
215
+ },
216
+ "layer_norm_eps": 1e-12,
217
+ "max_position_embeddings": 512,
218
+ "model_type": "bert",
219
+ "num_attention_heads": 12,
220
+ "num_hidden_layers": 12,
221
+ "pad_token_id": 0,
222
+ "pooler_fc_size": 768,
223
+ "pooler_num_attention_heads": 12,
224
+ "pooler_num_fc_layers": 3,
225
+ "pooler_size_per_head": 128,
226
+ "pooler_type": "first_token_transform",
227
+ "tie_word_embeddings": true,
228
+ "transformers_version": "5.6.2",
229
+ "type_vocab_size": 2,
230
+ "use_cache": false,
231
+ "vocab_size": 119547
232
+ }
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0f76a4a3e479ec6fbe6ff282a0ba81a63025242000ff311175a685e832f900
3
+ size 709373100
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "model_max_length": 512,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb243423fde16ca705cd9ad84acc9d405f1f57e5b3e25a17a8fdc7a57a0a0dc
3
+ size 5329
rosenxt-data-v10-7-7-full/bert-bio-bert-base-multilingual-cased/training_meta.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "token_based",
3
+ "base_model": "google-bert/bert-base-multilingual-cased",
4
+ "tagging_scheme": "bio",
5
+ "use_crf": false,
6
+ "dataset": "rosenxt-data-v10-7-7-full",
7
+ "label_list": [
8
+ "O",
9
+ "B-ACCOUNT_ID",
10
+ "I-ACCOUNT_ID",
11
+ "B-ADDRESS",
12
+ "I-ADDRESS",
13
+ "B-AGE",
14
+ "I-AGE",
15
+ "B-API_KEY",
16
+ "I-API_KEY",
17
+ "B-BANK_ACCOUNT",
18
+ "I-BANK_ACCOUNT",
19
+ "B-BANK_NAME",
20
+ "I-BANK_NAME",
21
+ "B-BIRTHDATE",
22
+ "I-BIRTHDATE",
23
+ "B-CARD_ISSUER",
24
+ "I-CARD_ISSUER",
25
+ "B-CARD_NUMBER",
26
+ "I-CARD_NUMBER",
27
+ "B-COORDINATE",
28
+ "I-COORDINATE",
29
+ "B-CVV",
30
+ "I-CVV",
31
+ "B-DATE",
32
+ "I-DATE",
33
+ "B-EMAIL",
34
+ "I-EMAIL",
35
+ "B-EMPLOYEE_ID",
36
+ "I-EMPLOYEE_ID",
37
+ "B-ETHNICITY",
38
+ "I-ETHNICITY",
39
+ "B-GENDER",
40
+ "I-GENDER",
41
+ "B-IBAN",
42
+ "I-IBAN",
43
+ "B-INSURANCE_ID",
44
+ "I-INSURANCE_ID",
45
+ "B-IP",
46
+ "I-IP",
47
+ "B-IP_ADDRESS",
48
+ "I-IP_ADDRESS",
49
+ "B-JOB_TITLE",
50
+ "I-JOB_TITLE",
51
+ "B-LICENSE",
52
+ "I-LICENSE",
53
+ "B-LOCATION",
54
+ "I-LOCATION",
55
+ "B-MARITAL",
56
+ "I-MARITAL",
57
+ "B-MEDICAL_INFO",
58
+ "I-MEDICAL_INFO",
59
+ "B-MONEY",
60
+ "I-MONEY",
61
+ "B-NATIONALITY",
62
+ "I-NATIONALITY",
63
+ "B-NATIONAL_ID",
64
+ "I-NATIONAL_ID",
65
+ "B-ORGANIZATION",
66
+ "I-ORGANIZATION",
67
+ "B-PASSPORT",
68
+ "I-PASSPORT",
69
+ "B-PASSPORT_NUM",
70
+ "I-PASSPORT_NUM",
71
+ "B-PASSWORD",
72
+ "I-PASSWORD",
73
+ "B-PERSON",
74
+ "I-PERSON",
75
+ "B-PHONE",
76
+ "I-PHONE",
77
+ "B-PIN",
78
+ "I-PIN",
79
+ "B-PLATE",
80
+ "I-PLATE",
81
+ "B-PREFIX",
82
+ "I-PREFIX",
83
+ "B-RELIGION",
84
+ "I-RELIGION",
85
+ "B-STUDENT_ID",
86
+ "I-STUDENT_ID",
87
+ "B-SWIFT",
88
+ "I-SWIFT",
89
+ "B-TICKET_ID",
90
+ "I-TICKET_ID",
91
+ "B-TIME",
92
+ "I-TIME",
93
+ "B-TIN",
94
+ "I-TIN",
95
+ "B-TRADE_UNION",
96
+ "I-TRADE_UNION",
97
+ "B-URL",
98
+ "I-URL",
99
+ "B-USERNAME",
100
+ "I-USERNAME",
101
+ "B-WALLET",
102
+ "I-WALLET",
103
+ "B-ZIP_CODE",
104
+ "I-ZIP_CODE"
105
+ ],
106
+ "max_seq_length": 512,
107
+ "timestamp": "2026-07-09T06:46:08.952563"
108
+ }