quynong commited on
Commit
de8a0b0
·
verified ·
1 Parent(s): aa2c7f4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  rosenxt-data-v10-7-7-full/evaluations/mbert/predictions.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  rosenxt-data-v10-7-7-full/evaluations/mbert/predictions.json filter=lfs diff=lfs merge=lfs -text
37
+ rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/tokenizer.json filter=lfs diff=lfs merge=lfs -text
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/config.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 1,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "O",
24
+ "1": "B-ACCOUNT_ID",
25
+ "2": "I-ACCOUNT_ID",
26
+ "3": "B-ADDRESS",
27
+ "4": "I-ADDRESS",
28
+ "5": "B-AGE",
29
+ "6": "I-AGE",
30
+ "7": "B-API_KEY",
31
+ "8": "I-API_KEY",
32
+ "9": "B-BANK_ACCOUNT",
33
+ "10": "I-BANK_ACCOUNT",
34
+ "11": "B-BANK_NAME",
35
+ "12": "I-BANK_NAME",
36
+ "13": "B-BIRTHDATE",
37
+ "14": "I-BIRTHDATE",
38
+ "15": "B-CARD_ISSUER",
39
+ "16": "I-CARD_ISSUER",
40
+ "17": "B-CARD_NUMBER",
41
+ "18": "I-CARD_NUMBER",
42
+ "19": "B-COORDINATE",
43
+ "20": "I-COORDINATE",
44
+ "21": "B-CVV",
45
+ "22": "I-CVV",
46
+ "23": "B-DATE",
47
+ "24": "I-DATE",
48
+ "25": "B-EMAIL",
49
+ "26": "I-EMAIL",
50
+ "27": "B-EMPLOYEE_ID",
51
+ "28": "I-EMPLOYEE_ID",
52
+ "29": "B-ETHNICITY",
53
+ "30": "I-ETHNICITY",
54
+ "31": "B-GENDER",
55
+ "32": "I-GENDER",
56
+ "33": "B-IBAN",
57
+ "34": "I-IBAN",
58
+ "35": "B-INSURANCE_ID",
59
+ "36": "I-INSURANCE_ID",
60
+ "37": "B-IP",
61
+ "38": "I-IP",
62
+ "39": "B-IP_ADDRESS",
63
+ "40": "I-IP_ADDRESS",
64
+ "41": "B-JOB_TITLE",
65
+ "42": "I-JOB_TITLE",
66
+ "43": "B-LICENSE",
67
+ "44": "I-LICENSE",
68
+ "45": "B-LOCATION",
69
+ "46": "I-LOCATION",
70
+ "47": "B-MARITAL",
71
+ "48": "I-MARITAL",
72
+ "49": "B-MEDICAL_INFO",
73
+ "50": "I-MEDICAL_INFO",
74
+ "51": "B-MONEY",
75
+ "52": "I-MONEY",
76
+ "53": "B-NATIONALITY",
77
+ "54": "I-NATIONALITY",
78
+ "55": "B-NATIONAL_ID",
79
+ "56": "I-NATIONAL_ID",
80
+ "57": "B-ORGANIZATION",
81
+ "58": "I-ORGANIZATION",
82
+ "59": "B-PASSPORT",
83
+ "60": "I-PASSPORT",
84
+ "61": "B-PASSPORT_NUM",
85
+ "62": "I-PASSPORT_NUM",
86
+ "63": "B-PASSWORD",
87
+ "64": "I-PASSWORD",
88
+ "65": "B-PERSON",
89
+ "66": "I-PERSON",
90
+ "67": "B-PHONE",
91
+ "68": "I-PHONE",
92
+ "69": "B-PIN",
93
+ "70": "I-PIN",
94
+ "71": "B-PLATE",
95
+ "72": "I-PLATE",
96
+ "73": "B-PREFIX",
97
+ "74": "I-PREFIX",
98
+ "75": "B-RELIGION",
99
+ "76": "I-RELIGION",
100
+ "77": "B-STUDENT_ID",
101
+ "78": "I-STUDENT_ID",
102
+ "79": "B-SWIFT",
103
+ "80": "I-SWIFT",
104
+ "81": "B-TICKET_ID",
105
+ "82": "I-TICKET_ID",
106
+ "83": "B-TIME",
107
+ "84": "I-TIME",
108
+ "85": "B-TIN",
109
+ "86": "I-TIN",
110
+ "87": "B-TRADE_UNION",
111
+ "88": "I-TRADE_UNION",
112
+ "89": "B-URL",
113
+ "90": "I-URL",
114
+ "91": "B-USERNAME",
115
+ "92": "I-USERNAME",
116
+ "93": "B-WALLET",
117
+ "94": "I-WALLET",
118
+ "95": "B-ZIP_CODE",
119
+ "96": "I-ZIP_CODE"
120
+ },
121
+ "initializer_cutoff_factor": 2.0,
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 1152,
124
+ "label2id": {
125
+ "B-ACCOUNT_ID": 1,
126
+ "B-ADDRESS": 3,
127
+ "B-AGE": 5,
128
+ "B-API_KEY": 7,
129
+ "B-BANK_ACCOUNT": 9,
130
+ "B-BANK_NAME": 11,
131
+ "B-BIRTHDATE": 13,
132
+ "B-CARD_ISSUER": 15,
133
+ "B-CARD_NUMBER": 17,
134
+ "B-COORDINATE": 19,
135
+ "B-CVV": 21,
136
+ "B-DATE": 23,
137
+ "B-EMAIL": 25,
138
+ "B-EMPLOYEE_ID": 27,
139
+ "B-ETHNICITY": 29,
140
+ "B-GENDER": 31,
141
+ "B-IBAN": 33,
142
+ "B-INSURANCE_ID": 35,
143
+ "B-IP": 37,
144
+ "B-IP_ADDRESS": 39,
145
+ "B-JOB_TITLE": 41,
146
+ "B-LICENSE": 43,
147
+ "B-LOCATION": 45,
148
+ "B-MARITAL": 47,
149
+ "B-MEDICAL_INFO": 49,
150
+ "B-MONEY": 51,
151
+ "B-NATIONALITY": 53,
152
+ "B-NATIONAL_ID": 55,
153
+ "B-ORGANIZATION": 57,
154
+ "B-PASSPORT": 59,
155
+ "B-PASSPORT_NUM": 61,
156
+ "B-PASSWORD": 63,
157
+ "B-PERSON": 65,
158
+ "B-PHONE": 67,
159
+ "B-PIN": 69,
160
+ "B-PLATE": 71,
161
+ "B-PREFIX": 73,
162
+ "B-RELIGION": 75,
163
+ "B-STUDENT_ID": 77,
164
+ "B-SWIFT": 79,
165
+ "B-TICKET_ID": 81,
166
+ "B-TIME": 83,
167
+ "B-TIN": 85,
168
+ "B-TRADE_UNION": 87,
169
+ "B-URL": 89,
170
+ "B-USERNAME": 91,
171
+ "B-WALLET": 93,
172
+ "B-ZIP_CODE": 95,
173
+ "I-ACCOUNT_ID": 2,
174
+ "I-ADDRESS": 4,
175
+ "I-AGE": 6,
176
+ "I-API_KEY": 8,
177
+ "I-BANK_ACCOUNT": 10,
178
+ "I-BANK_NAME": 12,
179
+ "I-BIRTHDATE": 14,
180
+ "I-CARD_ISSUER": 16,
181
+ "I-CARD_NUMBER": 18,
182
+ "I-COORDINATE": 20,
183
+ "I-CVV": 22,
184
+ "I-DATE": 24,
185
+ "I-EMAIL": 26,
186
+ "I-EMPLOYEE_ID": 28,
187
+ "I-ETHNICITY": 30,
188
+ "I-GENDER": 32,
189
+ "I-IBAN": 34,
190
+ "I-INSURANCE_ID": 36,
191
+ "I-IP": 38,
192
+ "I-IP_ADDRESS": 40,
193
+ "I-JOB_TITLE": 42,
194
+ "I-LICENSE": 44,
195
+ "I-LOCATION": 46,
196
+ "I-MARITAL": 48,
197
+ "I-MEDICAL_INFO": 50,
198
+ "I-MONEY": 52,
199
+ "I-NATIONALITY": 54,
200
+ "I-NATIONAL_ID": 56,
201
+ "I-ORGANIZATION": 58,
202
+ "I-PASSPORT": 60,
203
+ "I-PASSPORT_NUM": 62,
204
+ "I-PASSWORD": 64,
205
+ "I-PERSON": 66,
206
+ "I-PHONE": 68,
207
+ "I-PIN": 70,
208
+ "I-PLATE": 72,
209
+ "I-PREFIX": 74,
210
+ "I-RELIGION": 76,
211
+ "I-STUDENT_ID": 78,
212
+ "I-SWIFT": 80,
213
+ "I-TICKET_ID": 82,
214
+ "I-TIME": 84,
215
+ "I-TIN": 86,
216
+ "I-TRADE_UNION": 88,
217
+ "I-URL": 90,
218
+ "I-USERNAME": 92,
219
+ "I-WALLET": 94,
220
+ "I-ZIP_CODE": 96,
221
+ "O": 0
222
+ },
223
+ "layer_norm_eps": 1e-05,
224
+ "layer_types": [
225
+ "full_attention",
226
+ "sliding_attention",
227
+ "sliding_attention",
228
+ "full_attention",
229
+ "sliding_attention",
230
+ "sliding_attention",
231
+ "full_attention",
232
+ "sliding_attention",
233
+ "sliding_attention",
234
+ "full_attention",
235
+ "sliding_attention",
236
+ "sliding_attention",
237
+ "full_attention",
238
+ "sliding_attention",
239
+ "sliding_attention",
240
+ "full_attention",
241
+ "sliding_attention",
242
+ "sliding_attention",
243
+ "full_attention",
244
+ "sliding_attention",
245
+ "sliding_attention",
246
+ "full_attention"
247
+ ],
248
+ "local_attention": 128,
249
+ "mask_token_id": 4,
250
+ "max_position_embeddings": 8192,
251
+ "mlp_bias": false,
252
+ "mlp_dropout": 0.0,
253
+ "model_type": "modernbert",
254
+ "norm_bias": false,
255
+ "norm_eps": 1e-05,
256
+ "num_attention_heads": 12,
257
+ "num_hidden_layers": 22,
258
+ "pad_token_id": 0,
259
+ "position_embedding_type": "sans_pos",
260
+ "rope_parameters": {
261
+ "full_attention": {
262
+ "rope_theta": 160000,
263
+ "rope_type": "default"
264
+ },
265
+ "sliding_attention": {
266
+ "rope_theta": 160000,
267
+ "rope_type": "default"
268
+ }
269
+ },
270
+ "sep_token_id": 1,
271
+ "sparse_pred_ignore_index": -100,
272
+ "sparse_prediction": false,
273
+ "tie_word_embeddings": true,
274
+ "transformers_version": "5.6.2",
275
+ "use_cache": false,
276
+ "vocab_size": 256000
277
+ }
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2519736d26e34725f9e6c0b744bee09dc5aa71d91aa453663f834ff39697ab98
3
+ size 1230433652
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34b44a6dc8a0eef651bfa10e8325057530152606a69d9c3b6ae02efb1558f0a
3
+ size 34363286
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "<bos>",
7
+ "eos_token": "<eos>",
8
+ "extra_special_tokens": [
9
+ "<start_of_turn>",
10
+ "<end_of_turn>"
11
+ ],
12
+ "is_local": false,
13
+ "local_files_only": false,
14
+ "mask_token": "<mask>",
15
+ "model_input_names": [
16
+ "input_ids",
17
+ "attention_mask"
18
+ ],
19
+ "model_max_length": 8192,
20
+ "pad_token": "<pad>",
21
+ "padding_side": "right",
22
+ "sep_token": "<eos>",
23
+ "spaces_between_special_tokens": false,
24
+ "tokenizer_class": "TokenizersBackend",
25
+ "unk_token": "<unk>"
26
+ }
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05fae3ee386529673f23c8256327147052d2c2f0a5a8895f06bbc9a5b4b5469
3
+ size 5329
rosenxt-data-v10-7-7-full/bert-bio-mmBERT-base/training_meta.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "token_based",
3
+ "base_model": "jhu-clsp/mmBERT-base",
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": "2026-07-09T07:52:09.876870"
108
+ }