MaziyarPanahi's picture
Initial upload: privacy-filter fine-tuned for 55 Nemotron-PII labels
61f8bf4 verified
{
"architectures": [
"OpenAIPrivacyFilterForTokenClassification"
],
"attention_bias": true,
"attention_dropout": 0.0,
"bos_token_id": null,
"classifier_dropout": 0.0,
"default_n_ctx": 128000,
"dtype": "bfloat16",
"eos_token_id": 199999,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 640,
"id2label": {
"0": "O",
"1": "B-account_number",
"2": "I-account_number",
"3": "E-account_number",
"4": "S-account_number",
"5": "B-age",
"6": "I-age",
"7": "E-age",
"8": "S-age",
"9": "B-api_key",
"10": "I-api_key",
"11": "E-api_key",
"12": "S-api_key",
"13": "B-bank_routing_number",
"14": "I-bank_routing_number",
"15": "E-bank_routing_number",
"16": "S-bank_routing_number",
"17": "B-biometric_identifier",
"18": "I-biometric_identifier",
"19": "E-biometric_identifier",
"20": "S-biometric_identifier",
"21": "B-blood_type",
"22": "I-blood_type",
"23": "E-blood_type",
"24": "S-blood_type",
"25": "B-certificate_license_number",
"26": "I-certificate_license_number",
"27": "E-certificate_license_number",
"28": "S-certificate_license_number",
"29": "B-city",
"30": "I-city",
"31": "E-city",
"32": "S-city",
"33": "B-company_name",
"34": "I-company_name",
"35": "E-company_name",
"36": "S-company_name",
"37": "B-coordinate",
"38": "I-coordinate",
"39": "E-coordinate",
"40": "S-coordinate",
"41": "B-country",
"42": "I-country",
"43": "E-country",
"44": "S-country",
"45": "B-county",
"46": "I-county",
"47": "E-county",
"48": "S-county",
"49": "B-credit_debit_card",
"50": "I-credit_debit_card",
"51": "E-credit_debit_card",
"52": "S-credit_debit_card",
"53": "B-customer_id",
"54": "I-customer_id",
"55": "E-customer_id",
"56": "S-customer_id",
"57": "B-cvv",
"58": "I-cvv",
"59": "E-cvv",
"60": "S-cvv",
"61": "B-date",
"62": "I-date",
"63": "E-date",
"64": "S-date",
"65": "B-date_of_birth",
"66": "I-date_of_birth",
"67": "E-date_of_birth",
"68": "S-date_of_birth",
"69": "B-date_time",
"70": "I-date_time",
"71": "E-date_time",
"72": "S-date_time",
"73": "B-device_identifier",
"74": "I-device_identifier",
"75": "E-device_identifier",
"76": "S-device_identifier",
"77": "B-education_level",
"78": "I-education_level",
"79": "E-education_level",
"80": "S-education_level",
"81": "B-email",
"82": "I-email",
"83": "E-email",
"84": "S-email",
"85": "B-employee_id",
"86": "I-employee_id",
"87": "E-employee_id",
"88": "S-employee_id",
"89": "B-employment_status",
"90": "I-employment_status",
"91": "E-employment_status",
"92": "S-employment_status",
"93": "B-fax_number",
"94": "I-fax_number",
"95": "E-fax_number",
"96": "S-fax_number",
"97": "B-first_name",
"98": "I-first_name",
"99": "E-first_name",
"100": "S-first_name",
"101": "B-gender",
"102": "I-gender",
"103": "E-gender",
"104": "S-gender",
"105": "B-health_plan_beneficiary_number",
"106": "I-health_plan_beneficiary_number",
"107": "E-health_plan_beneficiary_number",
"108": "S-health_plan_beneficiary_number",
"109": "B-http_cookie",
"110": "I-http_cookie",
"111": "E-http_cookie",
"112": "S-http_cookie",
"113": "B-ipv4",
"114": "I-ipv4",
"115": "E-ipv4",
"116": "S-ipv4",
"117": "B-ipv6",
"118": "I-ipv6",
"119": "E-ipv6",
"120": "S-ipv6",
"121": "B-language",
"122": "I-language",
"123": "E-language",
"124": "S-language",
"125": "B-last_name",
"126": "I-last_name",
"127": "E-last_name",
"128": "S-last_name",
"129": "B-license_plate",
"130": "I-license_plate",
"131": "E-license_plate",
"132": "S-license_plate",
"133": "B-mac_address",
"134": "I-mac_address",
"135": "E-mac_address",
"136": "S-mac_address",
"137": "B-medical_record_number",
"138": "I-medical_record_number",
"139": "E-medical_record_number",
"140": "S-medical_record_number",
"141": "B-national_id",
"142": "I-national_id",
"143": "E-national_id",
"144": "S-national_id",
"145": "B-occupation",
"146": "I-occupation",
"147": "E-occupation",
"148": "S-occupation",
"149": "B-password",
"150": "I-password",
"151": "E-password",
"152": "S-password",
"153": "B-phone_number",
"154": "I-phone_number",
"155": "E-phone_number",
"156": "S-phone_number",
"157": "B-pin",
"158": "I-pin",
"159": "E-pin",
"160": "S-pin",
"161": "B-political_view",
"162": "I-political_view",
"163": "E-political_view",
"164": "S-political_view",
"165": "B-postcode",
"166": "I-postcode",
"167": "E-postcode",
"168": "S-postcode",
"169": "B-race_ethnicity",
"170": "I-race_ethnicity",
"171": "E-race_ethnicity",
"172": "S-race_ethnicity",
"173": "B-religious_belief",
"174": "I-religious_belief",
"175": "E-religious_belief",
"176": "S-religious_belief",
"177": "B-sexuality",
"178": "I-sexuality",
"179": "E-sexuality",
"180": "S-sexuality",
"181": "B-ssn",
"182": "I-ssn",
"183": "E-ssn",
"184": "S-ssn",
"185": "B-state",
"186": "I-state",
"187": "E-state",
"188": "S-state",
"189": "B-street_address",
"190": "I-street_address",
"191": "E-street_address",
"192": "S-street_address",
"193": "B-swift_bic",
"194": "I-swift_bic",
"195": "E-swift_bic",
"196": "S-swift_bic",
"197": "B-tax_id",
"198": "I-tax_id",
"199": "E-tax_id",
"200": "S-tax_id",
"201": "B-time",
"202": "I-time",
"203": "E-time",
"204": "S-time",
"205": "B-unique_id",
"206": "I-unique_id",
"207": "E-unique_id",
"208": "S-unique_id",
"209": "B-url",
"210": "I-url",
"211": "E-url",
"212": "S-url",
"213": "B-user_name",
"214": "I-user_name",
"215": "E-user_name",
"216": "S-user_name",
"217": "B-vehicle_identifier",
"218": "I-vehicle_identifier",
"219": "E-vehicle_identifier",
"220": "S-vehicle_identifier"
},
"initial_context_length": 4096,
"initializer_range": 0.02,
"intermediate_size": 640,
"label2id": {
"O": 0,
"B-account_number": 1,
"I-account_number": 2,
"E-account_number": 3,
"S-account_number": 4,
"B-age": 5,
"I-age": 6,
"E-age": 7,
"S-age": 8,
"B-api_key": 9,
"I-api_key": 10,
"E-api_key": 11,
"S-api_key": 12,
"B-bank_routing_number": 13,
"I-bank_routing_number": 14,
"E-bank_routing_number": 15,
"S-bank_routing_number": 16,
"B-biometric_identifier": 17,
"I-biometric_identifier": 18,
"E-biometric_identifier": 19,
"S-biometric_identifier": 20,
"B-blood_type": 21,
"I-blood_type": 22,
"E-blood_type": 23,
"S-blood_type": 24,
"B-certificate_license_number": 25,
"I-certificate_license_number": 26,
"E-certificate_license_number": 27,
"S-certificate_license_number": 28,
"B-city": 29,
"I-city": 30,
"E-city": 31,
"S-city": 32,
"B-company_name": 33,
"I-company_name": 34,
"E-company_name": 35,
"S-company_name": 36,
"B-coordinate": 37,
"I-coordinate": 38,
"E-coordinate": 39,
"S-coordinate": 40,
"B-country": 41,
"I-country": 42,
"E-country": 43,
"S-country": 44,
"B-county": 45,
"I-county": 46,
"E-county": 47,
"S-county": 48,
"B-credit_debit_card": 49,
"I-credit_debit_card": 50,
"E-credit_debit_card": 51,
"S-credit_debit_card": 52,
"B-customer_id": 53,
"I-customer_id": 54,
"E-customer_id": 55,
"S-customer_id": 56,
"B-cvv": 57,
"I-cvv": 58,
"E-cvv": 59,
"S-cvv": 60,
"B-date": 61,
"I-date": 62,
"E-date": 63,
"S-date": 64,
"B-date_of_birth": 65,
"I-date_of_birth": 66,
"E-date_of_birth": 67,
"S-date_of_birth": 68,
"B-date_time": 69,
"I-date_time": 70,
"E-date_time": 71,
"S-date_time": 72,
"B-device_identifier": 73,
"I-device_identifier": 74,
"E-device_identifier": 75,
"S-device_identifier": 76,
"B-education_level": 77,
"I-education_level": 78,
"E-education_level": 79,
"S-education_level": 80,
"B-email": 81,
"I-email": 82,
"E-email": 83,
"S-email": 84,
"B-employee_id": 85,
"I-employee_id": 86,
"E-employee_id": 87,
"S-employee_id": 88,
"B-employment_status": 89,
"I-employment_status": 90,
"E-employment_status": 91,
"S-employment_status": 92,
"B-fax_number": 93,
"I-fax_number": 94,
"E-fax_number": 95,
"S-fax_number": 96,
"B-first_name": 97,
"I-first_name": 98,
"E-first_name": 99,
"S-first_name": 100,
"B-gender": 101,
"I-gender": 102,
"E-gender": 103,
"S-gender": 104,
"B-health_plan_beneficiary_number": 105,
"I-health_plan_beneficiary_number": 106,
"E-health_plan_beneficiary_number": 107,
"S-health_plan_beneficiary_number": 108,
"B-http_cookie": 109,
"I-http_cookie": 110,
"E-http_cookie": 111,
"S-http_cookie": 112,
"B-ipv4": 113,
"I-ipv4": 114,
"E-ipv4": 115,
"S-ipv4": 116,
"B-ipv6": 117,
"I-ipv6": 118,
"E-ipv6": 119,
"S-ipv6": 120,
"B-language": 121,
"I-language": 122,
"E-language": 123,
"S-language": 124,
"B-last_name": 125,
"I-last_name": 126,
"E-last_name": 127,
"S-last_name": 128,
"B-license_plate": 129,
"I-license_plate": 130,
"E-license_plate": 131,
"S-license_plate": 132,
"B-mac_address": 133,
"I-mac_address": 134,
"E-mac_address": 135,
"S-mac_address": 136,
"B-medical_record_number": 137,
"I-medical_record_number": 138,
"E-medical_record_number": 139,
"S-medical_record_number": 140,
"B-national_id": 141,
"I-national_id": 142,
"E-national_id": 143,
"S-national_id": 144,
"B-occupation": 145,
"I-occupation": 146,
"E-occupation": 147,
"S-occupation": 148,
"B-password": 149,
"I-password": 150,
"E-password": 151,
"S-password": 152,
"B-phone_number": 153,
"I-phone_number": 154,
"E-phone_number": 155,
"S-phone_number": 156,
"B-pin": 157,
"I-pin": 158,
"E-pin": 159,
"S-pin": 160,
"B-political_view": 161,
"I-political_view": 162,
"E-political_view": 163,
"S-political_view": 164,
"B-postcode": 165,
"I-postcode": 166,
"E-postcode": 167,
"S-postcode": 168,
"B-race_ethnicity": 169,
"I-race_ethnicity": 170,
"E-race_ethnicity": 171,
"S-race_ethnicity": 172,
"B-religious_belief": 173,
"I-religious_belief": 174,
"E-religious_belief": 175,
"S-religious_belief": 176,
"B-sexuality": 177,
"I-sexuality": 178,
"E-sexuality": 179,
"S-sexuality": 180,
"B-ssn": 181,
"I-ssn": 182,
"E-ssn": 183,
"S-ssn": 184,
"B-state": 185,
"I-state": 186,
"E-state": 187,
"S-state": 188,
"B-street_address": 189,
"I-street_address": 190,
"E-street_address": 191,
"S-street_address": 192,
"B-swift_bic": 193,
"I-swift_bic": 194,
"E-swift_bic": 195,
"S-swift_bic": 196,
"B-tax_id": 197,
"I-tax_id": 198,
"E-tax_id": 199,
"S-tax_id": 200,
"B-time": 201,
"I-time": 202,
"E-time": 203,
"S-time": 204,
"B-unique_id": 205,
"I-unique_id": 206,
"E-unique_id": 207,
"S-unique_id": 208,
"B-url": 209,
"I-url": 210,
"E-url": 211,
"S-url": 212,
"B-user_name": 213,
"I-user_name": 214,
"E-user_name": 215,
"S-user_name": 216,
"B-vehicle_identifier": 217,
"I-vehicle_identifier": 218,
"E-vehicle_identifier": 219,
"S-vehicle_identifier": 220
},
"max_position_embeddings": 131072,
"model_type": "openai_privacy_filter",
"num_attention_heads": 14,
"num_experts_per_tok": 4,
"num_hidden_layers": 8,
"num_key_value_heads": 2,
"num_local_experts": 128,
"output_router_logits": false,
"pad_token_id": 199999,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 32.0,
"original_max_position_embeddings": 4096,
"rope_theta": 150000.0,
"rope_type": "yarn",
"truncate": false
},
"router_aux_loss_coef": 0.001,
"sliding_window": 128,
"tie_word_embeddings": false,
"transformers_version": "5.6.0.dev0",
"use_cache": true,
"vocab_size": 200064,
"transformers.js_config": {
"use_external_data_format": {
"model.onnx": 3,
"model_fp16.onnx": 2,
"model": 1
}
},
"num_labels": 221,
"opf_metadata": {
"category_version": "nemotron_fine_v1",
"encoding": "o200k_base",
"span_class_names": [
"O",
"account_number",
"age",
"api_key",
"bank_routing_number",
"biometric_identifier",
"blood_type",
"certificate_license_number",
"city",
"company_name",
"coordinate",
"country",
"county",
"credit_debit_card",
"customer_id",
"cvv",
"date",
"date_of_birth",
"date_time",
"device_identifier",
"education_level",
"email",
"employee_id",
"employment_status",
"fax_number",
"first_name",
"gender",
"health_plan_beneficiary_number",
"http_cookie",
"ipv4",
"ipv6",
"language",
"last_name",
"license_plate",
"mac_address",
"medical_record_number",
"national_id",
"occupation",
"password",
"phone_number",
"pin",
"political_view",
"postcode",
"race_ethnicity",
"religious_belief",
"sexuality",
"ssn",
"state",
"street_address",
"swift_bic",
"tax_id",
"time",
"unique_id",
"url",
"user_name",
"vehicle_identifier"
],
"ner_class_names": [
"O",
"B-account_number",
"I-account_number",
"E-account_number",
"S-account_number",
"B-age",
"I-age",
"E-age",
"S-age",
"B-api_key",
"I-api_key",
"E-api_key",
"S-api_key",
"B-bank_routing_number",
"I-bank_routing_number",
"E-bank_routing_number",
"S-bank_routing_number",
"B-biometric_identifier",
"I-biometric_identifier",
"E-biometric_identifier",
"S-biometric_identifier",
"B-blood_type",
"I-blood_type",
"E-blood_type",
"S-blood_type",
"B-certificate_license_number",
"I-certificate_license_number",
"E-certificate_license_number",
"S-certificate_license_number",
"B-city",
"I-city",
"E-city",
"S-city",
"B-company_name",
"I-company_name",
"E-company_name",
"S-company_name",
"B-coordinate",
"I-coordinate",
"E-coordinate",
"S-coordinate",
"B-country",
"I-country",
"E-country",
"S-country",
"B-county",
"I-county",
"E-county",
"S-county",
"B-credit_debit_card",
"I-credit_debit_card",
"E-credit_debit_card",
"S-credit_debit_card",
"B-customer_id",
"I-customer_id",
"E-customer_id",
"S-customer_id",
"B-cvv",
"I-cvv",
"E-cvv",
"S-cvv",
"B-date",
"I-date",
"E-date",
"S-date",
"B-date_of_birth",
"I-date_of_birth",
"E-date_of_birth",
"S-date_of_birth",
"B-date_time",
"I-date_time",
"E-date_time",
"S-date_time",
"B-device_identifier",
"I-device_identifier",
"E-device_identifier",
"S-device_identifier",
"B-education_level",
"I-education_level",
"E-education_level",
"S-education_level",
"B-email",
"I-email",
"E-email",
"S-email",
"B-employee_id",
"I-employee_id",
"E-employee_id",
"S-employee_id",
"B-employment_status",
"I-employment_status",
"E-employment_status",
"S-employment_status",
"B-fax_number",
"I-fax_number",
"E-fax_number",
"S-fax_number",
"B-first_name",
"I-first_name",
"E-first_name",
"S-first_name",
"B-gender",
"I-gender",
"E-gender",
"S-gender",
"B-health_plan_beneficiary_number",
"I-health_plan_beneficiary_number",
"E-health_plan_beneficiary_number",
"S-health_plan_beneficiary_number",
"B-http_cookie",
"I-http_cookie",
"E-http_cookie",
"S-http_cookie",
"B-ipv4",
"I-ipv4",
"E-ipv4",
"S-ipv4",
"B-ipv6",
"I-ipv6",
"E-ipv6",
"S-ipv6",
"B-language",
"I-language",
"E-language",
"S-language",
"B-last_name",
"I-last_name",
"E-last_name",
"S-last_name",
"B-license_plate",
"I-license_plate",
"E-license_plate",
"S-license_plate",
"B-mac_address",
"I-mac_address",
"E-mac_address",
"S-mac_address",
"B-medical_record_number",
"I-medical_record_number",
"E-medical_record_number",
"S-medical_record_number",
"B-national_id",
"I-national_id",
"E-national_id",
"S-national_id",
"B-occupation",
"I-occupation",
"E-occupation",
"S-occupation",
"B-password",
"I-password",
"E-password",
"S-password",
"B-phone_number",
"I-phone_number",
"E-phone_number",
"S-phone_number",
"B-pin",
"I-pin",
"E-pin",
"S-pin",
"B-political_view",
"I-political_view",
"E-political_view",
"S-political_view",
"B-postcode",
"I-postcode",
"E-postcode",
"S-postcode",
"B-race_ethnicity",
"I-race_ethnicity",
"E-race_ethnicity",
"S-race_ethnicity",
"B-religious_belief",
"I-religious_belief",
"E-religious_belief",
"S-religious_belief",
"B-sexuality",
"I-sexuality",
"E-sexuality",
"S-sexuality",
"B-ssn",
"I-ssn",
"E-ssn",
"S-ssn",
"B-state",
"I-state",
"E-state",
"S-state",
"B-street_address",
"I-street_address",
"E-street_address",
"S-street_address",
"B-swift_bic",
"I-swift_bic",
"E-swift_bic",
"S-swift_bic",
"B-tax_id",
"I-tax_id",
"E-tax_id",
"S-tax_id",
"B-time",
"I-time",
"E-time",
"S-time",
"B-unique_id",
"I-unique_id",
"E-unique_id",
"S-unique_id",
"B-url",
"I-url",
"E-url",
"S-url",
"B-user_name",
"I-user_name",
"E-user_name",
"S-user_name",
"B-vehicle_identifier",
"I-vehicle_identifier",
"E-vehicle_identifier",
"S-vehicle_identifier"
],
"inference_contract_version": 1
}
}