Upload folder using huggingface_hub
Browse files- nemotron/TokenBased-BERT/classification_report.json +338 -0
- nemotron/TokenBased-BERT/config.json +252 -0
- nemotron/TokenBased-BERT/model.safetensors +3 -0
- nemotron/TokenBased-BERT/predictions.json +0 -0
- nemotron/TokenBased-BERT/tokenizer.json +0 -0
- nemotron/TokenBased-BERT/tokenizer_config.json +16 -0
- nemotron/TokenBased-BERT/training_args.bin +3 -0
nemotron/TokenBased-BERT/classification_report.json
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ACCOUNT_NUMBER": {
|
| 3 |
+
"precision": 0.9657,
|
| 4 |
+
"recall": 0.9602,
|
| 5 |
+
"f1-score": 0.963,
|
| 6 |
+
"support": 176
|
| 7 |
+
},
|
| 8 |
+
"AGE": {
|
| 9 |
+
"precision": 0.9479,
|
| 10 |
+
"recall": 0.9681,
|
| 11 |
+
"f1-score": 0.9579,
|
| 12 |
+
"support": 94
|
| 13 |
+
},
|
| 14 |
+
"API_KEY": {
|
| 15 |
+
"precision": 1.0,
|
| 16 |
+
"recall": 0.9643,
|
| 17 |
+
"f1-score": 0.9818,
|
| 18 |
+
"support": 28
|
| 19 |
+
},
|
| 20 |
+
"BANK_ROUTING_NUMBER": {
|
| 21 |
+
"precision": 0.98,
|
| 22 |
+
"recall": 0.9703,
|
| 23 |
+
"f1-score": 0.9751,
|
| 24 |
+
"support": 101
|
| 25 |
+
},
|
| 26 |
+
"BIOMETRIC_IDENTIFIER": {
|
| 27 |
+
"precision": 0.9905,
|
| 28 |
+
"recall": 1.0,
|
| 29 |
+
"f1-score": 0.9952,
|
| 30 |
+
"support": 104
|
| 31 |
+
},
|
| 32 |
+
"BLOOD_TYPE": {
|
| 33 |
+
"precision": 1.0,
|
| 34 |
+
"recall": 1.0,
|
| 35 |
+
"f1-score": 1.0,
|
| 36 |
+
"support": 53
|
| 37 |
+
},
|
| 38 |
+
"CERTIFICATE_LICENSE_NUMBER": {
|
| 39 |
+
"precision": 1.0,
|
| 40 |
+
"recall": 0.9722,
|
| 41 |
+
"f1-score": 0.9859,
|
| 42 |
+
"support": 72
|
| 43 |
+
},
|
| 44 |
+
"CITY": {
|
| 45 |
+
"precision": 0.974,
|
| 46 |
+
"recall": 0.9677,
|
| 47 |
+
"f1-score": 0.9709,
|
| 48 |
+
"support": 155
|
| 49 |
+
},
|
| 50 |
+
"COMPANY_NAME": {
|
| 51 |
+
"precision": 0.9709,
|
| 52 |
+
"recall": 0.9471,
|
| 53 |
+
"f1-score": 0.9589,
|
| 54 |
+
"support": 529
|
| 55 |
+
},
|
| 56 |
+
"COORDINATE": {
|
| 57 |
+
"precision": 0.9787,
|
| 58 |
+
"recall": 1.0,
|
| 59 |
+
"f1-score": 0.9892,
|
| 60 |
+
"support": 92
|
| 61 |
+
},
|
| 62 |
+
"COUNTRY": {
|
| 63 |
+
"precision": 0.9854,
|
| 64 |
+
"recall": 0.9902,
|
| 65 |
+
"f1-score": 0.9878,
|
| 66 |
+
"support": 204
|
| 67 |
+
},
|
| 68 |
+
"COUNTY": {
|
| 69 |
+
"precision": 1.0,
|
| 70 |
+
"recall": 0.9461,
|
| 71 |
+
"f1-score": 0.9723,
|
| 72 |
+
"support": 167
|
| 73 |
+
},
|
| 74 |
+
"CREDIT_DEBIT_CARD": {
|
| 75 |
+
"precision": 1.0,
|
| 76 |
+
"recall": 0.9708,
|
| 77 |
+
"f1-score": 0.9852,
|
| 78 |
+
"support": 137
|
| 79 |
+
},
|
| 80 |
+
"CUSTOMER_ID": {
|
| 81 |
+
"precision": 0.9884,
|
| 82 |
+
"recall": 0.9942,
|
| 83 |
+
"f1-score": 0.9913,
|
| 84 |
+
"support": 171
|
| 85 |
+
},
|
| 86 |
+
"CVV": {
|
| 87 |
+
"precision": 1.0,
|
| 88 |
+
"recall": 0.9455,
|
| 89 |
+
"f1-score": 0.972,
|
| 90 |
+
"support": 55
|
| 91 |
+
},
|
| 92 |
+
"DATE": {
|
| 93 |
+
"precision": 0.969,
|
| 94 |
+
"recall": 0.9173,
|
| 95 |
+
"f1-score": 0.9425,
|
| 96 |
+
"support": 750
|
| 97 |
+
},
|
| 98 |
+
"DATE_OF_BIRTH": {
|
| 99 |
+
"precision": 0.9766,
|
| 100 |
+
"recall": 1.0,
|
| 101 |
+
"f1-score": 0.9881,
|
| 102 |
+
"support": 125
|
| 103 |
+
},
|
| 104 |
+
"DATE_TIME": {
|
| 105 |
+
"precision": 0.931,
|
| 106 |
+
"recall": 0.8526,
|
| 107 |
+
"f1-score": 0.8901,
|
| 108 |
+
"support": 95
|
| 109 |
+
},
|
| 110 |
+
"DEVICE_IDENTIFIER": {
|
| 111 |
+
"precision": 1.0,
|
| 112 |
+
"recall": 1.0,
|
| 113 |
+
"f1-score": 1.0,
|
| 114 |
+
"support": 18
|
| 115 |
+
},
|
| 116 |
+
"EDUCATION_LEVEL": {
|
| 117 |
+
"precision": 0.9649,
|
| 118 |
+
"recall": 0.9016,
|
| 119 |
+
"f1-score": 0.9322,
|
| 120 |
+
"support": 122
|
| 121 |
+
},
|
| 122 |
+
"EMAIL": {
|
| 123 |
+
"precision": 0.9974,
|
| 124 |
+
"recall": 0.9796,
|
| 125 |
+
"f1-score": 0.9884,
|
| 126 |
+
"support": 392
|
| 127 |
+
},
|
| 128 |
+
"EMPLOYEE_ID": {
|
| 129 |
+
"precision": 0.974,
|
| 130 |
+
"recall": 0.9375,
|
| 131 |
+
"f1-score": 0.9554,
|
| 132 |
+
"support": 80
|
| 133 |
+
},
|
| 134 |
+
"EMPLOYMENT_STATUS": {
|
| 135 |
+
"precision": 0.9278,
|
| 136 |
+
"recall": 0.9278,
|
| 137 |
+
"f1-score": 0.9278,
|
| 138 |
+
"support": 97
|
| 139 |
+
},
|
| 140 |
+
"FAX_NUMBER": {
|
| 141 |
+
"precision": 0.8971,
|
| 142 |
+
"recall": 0.9385,
|
| 143 |
+
"f1-score": 0.9173,
|
| 144 |
+
"support": 65
|
| 145 |
+
},
|
| 146 |
+
"FIRST_NAME": {
|
| 147 |
+
"precision": 0.9964,
|
| 148 |
+
"recall": 0.9808,
|
| 149 |
+
"f1-score": 0.9885,
|
| 150 |
+
"support": 835
|
| 151 |
+
},
|
| 152 |
+
"GENDER": {
|
| 153 |
+
"precision": 0.9208,
|
| 154 |
+
"recall": 0.9789,
|
| 155 |
+
"f1-score": 0.949,
|
| 156 |
+
"support": 95
|
| 157 |
+
},
|
| 158 |
+
"HEALTH_PLAN_BENEFICIARY_NUMBER": {
|
| 159 |
+
"precision": 1.0,
|
| 160 |
+
"recall": 0.9495,
|
| 161 |
+
"f1-score": 0.9741,
|
| 162 |
+
"support": 99
|
| 163 |
+
},
|
| 164 |
+
"HTTP_COOKIE": {
|
| 165 |
+
"precision": 0.9825,
|
| 166 |
+
"recall": 0.9492,
|
| 167 |
+
"f1-score": 0.9655,
|
| 168 |
+
"support": 59
|
| 169 |
+
},
|
| 170 |
+
"IPADDRESS": {
|
| 171 |
+
"precision": 1.0,
|
| 172 |
+
"recall": 0.975,
|
| 173 |
+
"f1-score": 0.9873,
|
| 174 |
+
"support": 80
|
| 175 |
+
},
|
| 176 |
+
"LANGUAGE": {
|
| 177 |
+
"precision": 0.9524,
|
| 178 |
+
"recall": 0.9677,
|
| 179 |
+
"f1-score": 0.96,
|
| 180 |
+
"support": 62
|
| 181 |
+
},
|
| 182 |
+
"LAST_NAME": {
|
| 183 |
+
"precision": 0.9874,
|
| 184 |
+
"recall": 0.9945,
|
| 185 |
+
"f1-score": 0.9909,
|
| 186 |
+
"support": 550
|
| 187 |
+
},
|
| 188 |
+
"LICENSE_PLATE": {
|
| 189 |
+
"precision": 0.9804,
|
| 190 |
+
"recall": 1.0,
|
| 191 |
+
"f1-score": 0.9901,
|
| 192 |
+
"support": 50
|
| 193 |
+
},
|
| 194 |
+
"MAC_ADDRESS": {
|
| 195 |
+
"precision": 1.0,
|
| 196 |
+
"recall": 0.9583,
|
| 197 |
+
"f1-score": 0.9787,
|
| 198 |
+
"support": 48
|
| 199 |
+
},
|
| 200 |
+
"MEDICAL_RECORD_NUMBER": {
|
| 201 |
+
"precision": 0.9829,
|
| 202 |
+
"recall": 1.0,
|
| 203 |
+
"f1-score": 0.9914,
|
| 204 |
+
"support": 115
|
| 205 |
+
},
|
| 206 |
+
"OCCUPATION": {
|
| 207 |
+
"precision": 0.9042,
|
| 208 |
+
"recall": 0.5975,
|
| 209 |
+
"f1-score": 0.7195,
|
| 210 |
+
"support": 395
|
| 211 |
+
},
|
| 212 |
+
"PASSWORD": {
|
| 213 |
+
"precision": 0.9844,
|
| 214 |
+
"recall": 0.9403,
|
| 215 |
+
"f1-score": 0.9618,
|
| 216 |
+
"support": 67
|
| 217 |
+
},
|
| 218 |
+
"PHONE_NUMBER": {
|
| 219 |
+
"precision": 0.9757,
|
| 220 |
+
"recall": 0.9663,
|
| 221 |
+
"f1-score": 0.971,
|
| 222 |
+
"support": 208
|
| 223 |
+
},
|
| 224 |
+
"PIN": {
|
| 225 |
+
"precision": 0.931,
|
| 226 |
+
"recall": 0.8438,
|
| 227 |
+
"f1-score": 0.8852,
|
| 228 |
+
"support": 64
|
| 229 |
+
},
|
| 230 |
+
"POLITICAL_VIEW": {
|
| 231 |
+
"precision": 0.8696,
|
| 232 |
+
"recall": 0.9524,
|
| 233 |
+
"f1-score": 0.9091,
|
| 234 |
+
"support": 63
|
| 235 |
+
},
|
| 236 |
+
"POSTCODE": {
|
| 237 |
+
"precision": 0.9516,
|
| 238 |
+
"recall": 0.9833,
|
| 239 |
+
"f1-score": 0.9672,
|
| 240 |
+
"support": 60
|
| 241 |
+
},
|
| 242 |
+
"RACE_ETHNICITY": {
|
| 243 |
+
"precision": 1.0,
|
| 244 |
+
"recall": 0.9906,
|
| 245 |
+
"f1-score": 0.9953,
|
| 246 |
+
"support": 106
|
| 247 |
+
},
|
| 248 |
+
"RELIGIOUS_BELIEF": {
|
| 249 |
+
"precision": 0.88,
|
| 250 |
+
"recall": 0.8,
|
| 251 |
+
"f1-score": 0.8381,
|
| 252 |
+
"support": 55
|
| 253 |
+
},
|
| 254 |
+
"SEXUALITY": {
|
| 255 |
+
"precision": 0.8684,
|
| 256 |
+
"recall": 1.0,
|
| 257 |
+
"f1-score": 0.9296,
|
| 258 |
+
"support": 33
|
| 259 |
+
},
|
| 260 |
+
"SSN": {
|
| 261 |
+
"precision": 0.9892,
|
| 262 |
+
"recall": 1.0,
|
| 263 |
+
"f1-score": 0.9946,
|
| 264 |
+
"support": 92
|
| 265 |
+
},
|
| 266 |
+
"STATE": {
|
| 267 |
+
"precision": 0.9683,
|
| 268 |
+
"recall": 0.9531,
|
| 269 |
+
"f1-score": 0.9606,
|
| 270 |
+
"support": 192
|
| 271 |
+
},
|
| 272 |
+
"STREET_ADDRESS": {
|
| 273 |
+
"precision": 0.9882,
|
| 274 |
+
"recall": 0.9941,
|
| 275 |
+
"f1-score": 0.9912,
|
| 276 |
+
"support": 169
|
| 277 |
+
},
|
| 278 |
+
"SWIFT_BIC": {
|
| 279 |
+
"precision": 0.9574,
|
| 280 |
+
"recall": 1.0,
|
| 281 |
+
"f1-score": 0.9783,
|
| 282 |
+
"support": 45
|
| 283 |
+
},
|
| 284 |
+
"TAX_ID": {
|
| 285 |
+
"precision": 0.9091,
|
| 286 |
+
"recall": 0.9091,
|
| 287 |
+
"f1-score": 0.9091,
|
| 288 |
+
"support": 11
|
| 289 |
+
},
|
| 290 |
+
"TIME": {
|
| 291 |
+
"precision": 0.9492,
|
| 292 |
+
"recall": 0.7249,
|
| 293 |
+
"f1-score": 0.822,
|
| 294 |
+
"support": 309
|
| 295 |
+
},
|
| 296 |
+
"UNIQUE_ID": {
|
| 297 |
+
"precision": 0.8333,
|
| 298 |
+
"recall": 0.9091,
|
| 299 |
+
"f1-score": 0.8696,
|
| 300 |
+
"support": 11
|
| 301 |
+
},
|
| 302 |
+
"URL": {
|
| 303 |
+
"precision": 1.0,
|
| 304 |
+
"recall": 0.9736,
|
| 305 |
+
"f1-score": 0.9866,
|
| 306 |
+
"support": 379
|
| 307 |
+
},
|
| 308 |
+
"USER_NAME": {
|
| 309 |
+
"precision": 0.9699,
|
| 310 |
+
"recall": 0.9348,
|
| 311 |
+
"f1-score": 0.952,
|
| 312 |
+
"support": 138
|
| 313 |
+
},
|
| 314 |
+
"VEHICLE_IDENTIFIER": {
|
| 315 |
+
"precision": 1.0,
|
| 316 |
+
"recall": 1.0,
|
| 317 |
+
"f1-score": 1.0,
|
| 318 |
+
"support": 51
|
| 319 |
+
},
|
| 320 |
+
"OVERALL_MICRO": {
|
| 321 |
+
"precision": 0.9744,
|
| 322 |
+
"recall": 0.9367,
|
| 323 |
+
"f1-score": 0.9552,
|
| 324 |
+
"support": 8323
|
| 325 |
+
},
|
| 326 |
+
"OVERALL_MACRO": {
|
| 327 |
+
"precision": 0.9651,
|
| 328 |
+
"recall": 0.9487,
|
| 329 |
+
"f1-score": 0.9556,
|
| 330 |
+
"support": 8323
|
| 331 |
+
},
|
| 332 |
+
"OVERALL_WEIGHTED": {
|
| 333 |
+
"precision": 0.9733,
|
| 334 |
+
"recall": 0.9367,
|
| 335 |
+
"f1-score": 0.9527,
|
| 336 |
+
"support": 8323
|
| 337 |
+
}
|
| 338 |
+
}
|
nemotron/TokenBased-BERT/config.json
ADDED
|
@@ -0,0 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "O",
|
| 17 |
+
"1": "B-ACCOUNT_NUMBER",
|
| 18 |
+
"2": "I-ACCOUNT_NUMBER",
|
| 19 |
+
"3": "B-AGE",
|
| 20 |
+
"4": "I-AGE",
|
| 21 |
+
"5": "B-API_KEY",
|
| 22 |
+
"6": "I-API_KEY",
|
| 23 |
+
"7": "B-BANK_ROUTING_NUMBER",
|
| 24 |
+
"8": "I-BANK_ROUTING_NUMBER",
|
| 25 |
+
"9": "B-BIOMETRIC_IDENTIFIER",
|
| 26 |
+
"10": "I-BIOMETRIC_IDENTIFIER",
|
| 27 |
+
"11": "B-BLOOD_TYPE",
|
| 28 |
+
"12": "I-BLOOD_TYPE",
|
| 29 |
+
"13": "B-CERTIFICATE_LICENSE_NUMBER",
|
| 30 |
+
"14": "I-CERTIFICATE_LICENSE_NUMBER",
|
| 31 |
+
"15": "B-CITY",
|
| 32 |
+
"16": "I-CITY",
|
| 33 |
+
"17": "B-COMPANY_NAME",
|
| 34 |
+
"18": "I-COMPANY_NAME",
|
| 35 |
+
"19": "B-COORDINATE",
|
| 36 |
+
"20": "I-COORDINATE",
|
| 37 |
+
"21": "B-COUNTRY",
|
| 38 |
+
"22": "I-COUNTRY",
|
| 39 |
+
"23": "B-COUNTY",
|
| 40 |
+
"24": "I-COUNTY",
|
| 41 |
+
"25": "B-CREDIT_DEBIT_CARD",
|
| 42 |
+
"26": "I-CREDIT_DEBIT_CARD",
|
| 43 |
+
"27": "B-CUSTOMER_ID",
|
| 44 |
+
"28": "I-CUSTOMER_ID",
|
| 45 |
+
"29": "B-CVV",
|
| 46 |
+
"30": "I-CVV",
|
| 47 |
+
"31": "B-DATE",
|
| 48 |
+
"32": "I-DATE",
|
| 49 |
+
"33": "B-DATE_OF_BIRTH",
|
| 50 |
+
"34": "I-DATE_OF_BIRTH",
|
| 51 |
+
"35": "B-DATE_TIME",
|
| 52 |
+
"36": "I-DATE_TIME",
|
| 53 |
+
"37": "B-DEVICE_IDENTIFIER",
|
| 54 |
+
"38": "I-DEVICE_IDENTIFIER",
|
| 55 |
+
"39": "B-EDUCATION_LEVEL",
|
| 56 |
+
"40": "I-EDUCATION_LEVEL",
|
| 57 |
+
"41": "B-EMAIL",
|
| 58 |
+
"42": "I-EMAIL",
|
| 59 |
+
"43": "B-EMPLOYEE_ID",
|
| 60 |
+
"44": "I-EMPLOYEE_ID",
|
| 61 |
+
"45": "B-EMPLOYMENT_STATUS",
|
| 62 |
+
"46": "I-EMPLOYMENT_STATUS",
|
| 63 |
+
"47": "B-FAX_NUMBER",
|
| 64 |
+
"48": "I-FAX_NUMBER",
|
| 65 |
+
"49": "B-FIRST_NAME",
|
| 66 |
+
"50": "I-FIRST_NAME",
|
| 67 |
+
"51": "B-GENDER",
|
| 68 |
+
"52": "I-GENDER",
|
| 69 |
+
"53": "B-HEALTH_PLAN_BENEFICIARY_NUMBER",
|
| 70 |
+
"54": "I-HEALTH_PLAN_BENEFICIARY_NUMBER",
|
| 71 |
+
"55": "B-HTTP_COOKIE",
|
| 72 |
+
"56": "I-HTTP_COOKIE",
|
| 73 |
+
"57": "B-IPADDRESS",
|
| 74 |
+
"58": "I-IPADDRESS",
|
| 75 |
+
"59": "B-LANGUAGE",
|
| 76 |
+
"60": "I-LANGUAGE",
|
| 77 |
+
"61": "B-LAST_NAME",
|
| 78 |
+
"62": "I-LAST_NAME",
|
| 79 |
+
"63": "B-LICENSE_PLATE",
|
| 80 |
+
"64": "I-LICENSE_PLATE",
|
| 81 |
+
"65": "B-MAC_ADDRESS",
|
| 82 |
+
"66": "I-MAC_ADDRESS",
|
| 83 |
+
"67": "B-MEDICAL_RECORD_NUMBER",
|
| 84 |
+
"68": "I-MEDICAL_RECORD_NUMBER",
|
| 85 |
+
"69": "B-NATIONAL_ID",
|
| 86 |
+
"70": "I-NATIONAL_ID",
|
| 87 |
+
"71": "B-OCCUPATION",
|
| 88 |
+
"72": "I-OCCUPATION",
|
| 89 |
+
"73": "B-PASSWORD",
|
| 90 |
+
"74": "I-PASSWORD",
|
| 91 |
+
"75": "B-PHONE_NUMBER",
|
| 92 |
+
"76": "I-PHONE_NUMBER",
|
| 93 |
+
"77": "B-PIN",
|
| 94 |
+
"78": "I-PIN",
|
| 95 |
+
"79": "B-POLITICAL_VIEW",
|
| 96 |
+
"80": "I-POLITICAL_VIEW",
|
| 97 |
+
"81": "B-POSTCODE",
|
| 98 |
+
"82": "I-POSTCODE",
|
| 99 |
+
"83": "B-RACE_ETHNICITY",
|
| 100 |
+
"84": "I-RACE_ETHNICITY",
|
| 101 |
+
"85": "B-RELIGIOUS_BELIEF",
|
| 102 |
+
"86": "I-RELIGIOUS_BELIEF",
|
| 103 |
+
"87": "B-SEXUALITY",
|
| 104 |
+
"88": "I-SEXUALITY",
|
| 105 |
+
"89": "B-SSN",
|
| 106 |
+
"90": "I-SSN",
|
| 107 |
+
"91": "B-STATE",
|
| 108 |
+
"92": "I-STATE",
|
| 109 |
+
"93": "B-STREET_ADDRESS",
|
| 110 |
+
"94": "I-STREET_ADDRESS",
|
| 111 |
+
"95": "B-SWIFT_BIC",
|
| 112 |
+
"96": "I-SWIFT_BIC",
|
| 113 |
+
"97": "B-TAX_ID",
|
| 114 |
+
"98": "I-TAX_ID",
|
| 115 |
+
"99": "B-TIME",
|
| 116 |
+
"100": "I-TIME",
|
| 117 |
+
"101": "B-UNIQUE_ID",
|
| 118 |
+
"102": "I-UNIQUE_ID",
|
| 119 |
+
"103": "B-URL",
|
| 120 |
+
"104": "I-URL",
|
| 121 |
+
"105": "B-USER_NAME",
|
| 122 |
+
"106": "I-USER_NAME",
|
| 123 |
+
"107": "B-VEHICLE_IDENTIFIER",
|
| 124 |
+
"108": "I-VEHICLE_IDENTIFIER"
|
| 125 |
+
},
|
| 126 |
+
"initializer_range": 0.02,
|
| 127 |
+
"intermediate_size": 3072,
|
| 128 |
+
"is_decoder": false,
|
| 129 |
+
"label2id": {
|
| 130 |
+
"B-ACCOUNT_NUMBER": 1,
|
| 131 |
+
"B-AGE": 3,
|
| 132 |
+
"B-API_KEY": 5,
|
| 133 |
+
"B-BANK_ROUTING_NUMBER": 7,
|
| 134 |
+
"B-BIOMETRIC_IDENTIFIER": 9,
|
| 135 |
+
"B-BLOOD_TYPE": 11,
|
| 136 |
+
"B-CERTIFICATE_LICENSE_NUMBER": 13,
|
| 137 |
+
"B-CITY": 15,
|
| 138 |
+
"B-COMPANY_NAME": 17,
|
| 139 |
+
"B-COORDINATE": 19,
|
| 140 |
+
"B-COUNTRY": 21,
|
| 141 |
+
"B-COUNTY": 23,
|
| 142 |
+
"B-CREDIT_DEBIT_CARD": 25,
|
| 143 |
+
"B-CUSTOMER_ID": 27,
|
| 144 |
+
"B-CVV": 29,
|
| 145 |
+
"B-DATE": 31,
|
| 146 |
+
"B-DATE_OF_BIRTH": 33,
|
| 147 |
+
"B-DATE_TIME": 35,
|
| 148 |
+
"B-DEVICE_IDENTIFIER": 37,
|
| 149 |
+
"B-EDUCATION_LEVEL": 39,
|
| 150 |
+
"B-EMAIL": 41,
|
| 151 |
+
"B-EMPLOYEE_ID": 43,
|
| 152 |
+
"B-EMPLOYMENT_STATUS": 45,
|
| 153 |
+
"B-FAX_NUMBER": 47,
|
| 154 |
+
"B-FIRST_NAME": 49,
|
| 155 |
+
"B-GENDER": 51,
|
| 156 |
+
"B-HEALTH_PLAN_BENEFICIARY_NUMBER": 53,
|
| 157 |
+
"B-HTTP_COOKIE": 55,
|
| 158 |
+
"B-IPADDRESS": 57,
|
| 159 |
+
"B-LANGUAGE": 59,
|
| 160 |
+
"B-LAST_NAME": 61,
|
| 161 |
+
"B-LICENSE_PLATE": 63,
|
| 162 |
+
"B-MAC_ADDRESS": 65,
|
| 163 |
+
"B-MEDICAL_RECORD_NUMBER": 67,
|
| 164 |
+
"B-NATIONAL_ID": 69,
|
| 165 |
+
"B-OCCUPATION": 71,
|
| 166 |
+
"B-PASSWORD": 73,
|
| 167 |
+
"B-PHONE_NUMBER": 75,
|
| 168 |
+
"B-PIN": 77,
|
| 169 |
+
"B-POLITICAL_VIEW": 79,
|
| 170 |
+
"B-POSTCODE": 81,
|
| 171 |
+
"B-RACE_ETHNICITY": 83,
|
| 172 |
+
"B-RELIGIOUS_BELIEF": 85,
|
| 173 |
+
"B-SEXUALITY": 87,
|
| 174 |
+
"B-SSN": 89,
|
| 175 |
+
"B-STATE": 91,
|
| 176 |
+
"B-STREET_ADDRESS": 93,
|
| 177 |
+
"B-SWIFT_BIC": 95,
|
| 178 |
+
"B-TAX_ID": 97,
|
| 179 |
+
"B-TIME": 99,
|
| 180 |
+
"B-UNIQUE_ID": 101,
|
| 181 |
+
"B-URL": 103,
|
| 182 |
+
"B-USER_NAME": 105,
|
| 183 |
+
"B-VEHICLE_IDENTIFIER": 107,
|
| 184 |
+
"I-ACCOUNT_NUMBER": 2,
|
| 185 |
+
"I-AGE": 4,
|
| 186 |
+
"I-API_KEY": 6,
|
| 187 |
+
"I-BANK_ROUTING_NUMBER": 8,
|
| 188 |
+
"I-BIOMETRIC_IDENTIFIER": 10,
|
| 189 |
+
"I-BLOOD_TYPE": 12,
|
| 190 |
+
"I-CERTIFICATE_LICENSE_NUMBER": 14,
|
| 191 |
+
"I-CITY": 16,
|
| 192 |
+
"I-COMPANY_NAME": 18,
|
| 193 |
+
"I-COORDINATE": 20,
|
| 194 |
+
"I-COUNTRY": 22,
|
| 195 |
+
"I-COUNTY": 24,
|
| 196 |
+
"I-CREDIT_DEBIT_CARD": 26,
|
| 197 |
+
"I-CUSTOMER_ID": 28,
|
| 198 |
+
"I-CVV": 30,
|
| 199 |
+
"I-DATE": 32,
|
| 200 |
+
"I-DATE_OF_BIRTH": 34,
|
| 201 |
+
"I-DATE_TIME": 36,
|
| 202 |
+
"I-DEVICE_IDENTIFIER": 38,
|
| 203 |
+
"I-EDUCATION_LEVEL": 40,
|
| 204 |
+
"I-EMAIL": 42,
|
| 205 |
+
"I-EMPLOYEE_ID": 44,
|
| 206 |
+
"I-EMPLOYMENT_STATUS": 46,
|
| 207 |
+
"I-FAX_NUMBER": 48,
|
| 208 |
+
"I-FIRST_NAME": 50,
|
| 209 |
+
"I-GENDER": 52,
|
| 210 |
+
"I-HEALTH_PLAN_BENEFICIARY_NUMBER": 54,
|
| 211 |
+
"I-HTTP_COOKIE": 56,
|
| 212 |
+
"I-IPADDRESS": 58,
|
| 213 |
+
"I-LANGUAGE": 60,
|
| 214 |
+
"I-LAST_NAME": 62,
|
| 215 |
+
"I-LICENSE_PLATE": 64,
|
| 216 |
+
"I-MAC_ADDRESS": 66,
|
| 217 |
+
"I-MEDICAL_RECORD_NUMBER": 68,
|
| 218 |
+
"I-NATIONAL_ID": 70,
|
| 219 |
+
"I-OCCUPATION": 72,
|
| 220 |
+
"I-PASSWORD": 74,
|
| 221 |
+
"I-PHONE_NUMBER": 76,
|
| 222 |
+
"I-PIN": 78,
|
| 223 |
+
"I-POLITICAL_VIEW": 80,
|
| 224 |
+
"I-POSTCODE": 82,
|
| 225 |
+
"I-RACE_ETHNICITY": 84,
|
| 226 |
+
"I-RELIGIOUS_BELIEF": 86,
|
| 227 |
+
"I-SEXUALITY": 88,
|
| 228 |
+
"I-SSN": 90,
|
| 229 |
+
"I-STATE": 92,
|
| 230 |
+
"I-STREET_ADDRESS": 94,
|
| 231 |
+
"I-SWIFT_BIC": 96,
|
| 232 |
+
"I-TAX_ID": 98,
|
| 233 |
+
"I-TIME": 100,
|
| 234 |
+
"I-UNIQUE_ID": 102,
|
| 235 |
+
"I-URL": 104,
|
| 236 |
+
"I-USER_NAME": 106,
|
| 237 |
+
"I-VEHICLE_IDENTIFIER": 108,
|
| 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 |
+
"position_embedding_type": "absolute",
|
| 247 |
+
"tie_word_embeddings": true,
|
| 248 |
+
"transformers_version": "5.6.2",
|
| 249 |
+
"type_vocab_size": 2,
|
| 250 |
+
"use_cache": false,
|
| 251 |
+
"vocab_size": 30522
|
| 252 |
+
}
|
nemotron/TokenBased-BERT/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0d6ea66ae71453dbb57f2c3f9cacb33a8cfeabd101effec81be6d8b65229a74
|
| 3 |
+
size 435925196
|
nemotron/TokenBased-BERT/predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
nemotron/TokenBased-BERT/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
nemotron/TokenBased-BERT/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": true,
|
| 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 |
+
}
|
nemotron/TokenBased-BERT/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0177829520d218929a88f6460404a19799f7d93ba89980a581d9fc457b65241e
|
| 3 |
+
size 5265
|