Upload fine-tuned BERT PII detector (ONNX format)

config.json

@@ -0,0 +1,139 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-BOD",
+    "1": "B-BUILDING",
+    "2": "B-CITY",
+    "3": "B-COUNTRY",
+    "4": "B-DATE",
+    "5": "B-DRIVERLICENSE",
+    "6": "B-EMAIL",
+    "7": "B-GEOCOORD",
+    "8": "B-GIVENNAME1",
+    "9": "B-GIVENNAME2",
+    "10": "B-IDCARD",
+    "11": "B-IP",
+    "12": "B-LASTNAME1",
+    "13": "B-LASTNAME2",
+    "14": "B-LASTNAME3",
+    "15": "B-PASS",
+    "16": "B-PASSPORT",
+    "17": "B-POSTCODE",
+    "18": "B-SECADDRESS",
+    "19": "B-SEX",
+    "20": "B-SOCIALNUMBER",
+    "21": "B-STATE",
+    "22": "B-STREET",
+    "23": "B-TEL",
+    "24": "B-TIME",
+    "25": "B-TITLE",
+    "26": "B-USERNAME",
+    "27": "I-BOD",
+    "28": "I-BUILDING",
+    "29": "I-CITY",
+    "30": "I-COUNTRY",
+    "31": "I-DATE",
+    "32": "I-DRIVERLICENSE",
+    "33": "I-EMAIL",
+    "34": "I-GEOCOORD",
+    "35": "I-GIVENNAME1",
+    "36": "I-GIVENNAME2",
+    "37": "I-IDCARD",
+    "38": "I-IP",
+    "39": "I-LASTNAME1",
+    "40": "I-LASTNAME2",
+    "41": "I-LASTNAME3",
+    "42": "I-PASS",
+    "43": "I-PASSPORT",
+    "44": "I-POSTCODE",
+    "45": "I-SECADDRESS",
+    "46": "I-SEX",
+    "47": "I-SOCIALNUMBER",
+    "48": "I-STATE",
+    "49": "I-STREET",
+    "50": "I-TEL",
+    "51": "I-TIME",
+    "52": "I-TITLE",
+    "53": "I-USERNAME",
+    "54": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-BOD": 0,
+    "B-BUILDING": 1,
+    "B-CITY": 2,
+    "B-COUNTRY": 3,
+    "B-DATE": 4,
+    "B-DRIVERLICENSE": 5,
+    "B-EMAIL": 6,
+    "B-GEOCOORD": 7,
+    "B-GIVENNAME1": 8,
+    "B-GIVENNAME2": 9,
+    "B-IDCARD": 10,
+    "B-IP": 11,
+    "B-LASTNAME1": 12,
+    "B-LASTNAME2": 13,
+    "B-LASTNAME3": 14,
+    "B-PASS": 15,
+    "B-PASSPORT": 16,
+    "B-POSTCODE": 17,
+    "B-SECADDRESS": 18,
+    "B-SEX": 19,
+    "B-SOCIALNUMBER": 20,
+    "B-STATE": 21,
+    "B-STREET": 22,
+    "B-TEL": 23,
+    "B-TIME": 24,
+    "B-TITLE": 25,
+    "B-USERNAME": 26,
+    "I-BOD": 27,
+    "I-BUILDING": 28,
+    "I-CITY": 29,
+    "I-COUNTRY": 30,
+    "I-DATE": 31,
+    "I-DRIVERLICENSE": 32,
+    "I-EMAIL": 33,
+    "I-GEOCOORD": 34,
+    "I-GIVENNAME1": 35,
+    "I-GIVENNAME2": 36,
+    "I-IDCARD": 37,
+    "I-IP": 38,
+    "I-LASTNAME1": 39,
+    "I-LASTNAME2": 40,
+    "I-LASTNAME3": 41,
+    "I-PASS": 42,
+    "I-PASSPORT": 43,
+    "I-POSTCODE": 44,
+    "I-SECADDRESS": 45,
+    "I-SEX": 46,
+    "I-SOCIALNUMBER": 47,
+    "I-STATE": 48,
+    "I-STREET": 49,
+    "I-TEL": 50,
+    "I-TIME": 51,
+    "I-TITLE": 52,
+    "I-USERNAME": 53,
+    "O": 54
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49463c26f0373723c442613cbfc5e87f9f4bf88869ffa9330bc8363448cdb20a
+size 435990412

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}