Upload 9 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,337 @@
 ---
+language: en
 license: apache-2.0
+tags:
+- bert
+- token-classification
+- ner
+- pii
+- privacy
+- onnx
+- personal-information
+datasets:
+- custom
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: bert-pii-onnx
+  results: []
 ---
+
+# BERT PII Detection Model (ONNX)
+
+This model is a BERT-based token classification model fine-tuned for detecting Personally Identifiable Information (PII) in text. The model is provided in ONNX format for efficient inference across different platforms.
+
+## Model Description
+
+- **Model Type:** Token Classification (Named Entity Recognition)
+- **Base Model:** `bert-base-uncased` (Google BERT)
+- **Format:** ONNX
+- **Language:** English
+- **License:** Apache 2.0
+- **Training Dataset:** ai4privacy/pii-masking-300k
+
+## Intended Use
+
+This model is designed to identify and classify various types of personally identifiable information in text, including but not limited to:
+
+### Supported PII Categories
+
+The model can detect 27 different types of PII entities:
+
+#### Personal Identifiers
+- **GIVENNAME1, GIVENNAME2** - First/given names
+- **LASTNAME1, LASTNAME2, LASTNAME3** - Last/family names
+- **USERNAME** - Usernames
+- **TITLE** - Personal titles
+- **SEX** - Gender information
+
+#### Contact Information
+- **EMAIL** - Email addresses
+- **TEL** - Telephone numbers
+- **IP** - IP addresses
+
+#### Location Information
+- **STREET** - Street addresses
+- **CITY** - City names
+- **STATE** - State/province names
+- **COUNTRY** - Country names
+- **POSTCODE** - Postal/ZIP codes
+- **BUILDING** - Building names/numbers
+- **SECADDRESS** - Secondary addresses
+- **GEOCOORD** - Geographic coordinates
+
+#### Identification Documents
+- **PASSPORT** - Passport numbers
+- **IDCARD** - ID card numbers
+- **DRIVERLICENSE** - Driver's license numbers
+- **SOCIALNUMBER** - Social security numbers
+- **PASS** - Password information
+
+#### Temporal Information
+- **DATE** - Date information
+- **TIME** - Time information
+- **BOD** - Birth date
+
+The model uses BIO (Begin-Inside-Outside) tagging scheme, where:
+- `B-[ENTITY]` marks the beginning of an entity
+- `I-[ENTITY]` marks the continuation of an entity
+- `O` marks tokens that are not PII
+
+## Usage
+
+### Requirements
+
+```bash
+pip install onnxruntime transformers tokenizers
+```
+
+### Python Example
+
+```python
+import onnxruntime as ort
+from transformers import AutoTokenizer
+import numpy as np
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("path/to/model")
+
+# Load ONNX model
+session = ort.InferenceSession("onnx/model.onnx")
+
+# Prepare input text
+text = "My name is John Smith and my email is [email protected]"
+inputs = tokenizer(text, return_tensors="np", padding=True, truncation=True)
+
+# Run inference
+outputs = session.run(
+    None,
+    {
+        "input_ids": inputs["input_ids"].astype(np.int64),
+        "attention_mask": inputs["attention_mask"].astype(np.int64),
+        "token_type_ids": inputs["token_type_ids"].astype(np.int64)
+    }
+)
+
+# Get predictions
+logits = outputs[0]
+predictions = np.argmax(logits, axis=-1)
+
+# Map predictions to labels
+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"
+}
+
+# Decode predictions
+tokens = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])
+labels = [id2label[pred] for pred in predictions[0]]
+
+for token, label in zip(tokens, labels):
+    if token not in ["[CLS]", "[SEP]", "[PAD]"]:
+        print(f"{token}: {label}")
+```
+
+### JavaScript/Node.js Example
+
+```javascript
+const ort = require('onnxruntime-node');
+const { AutoTokenizer } = require('@xenova/transformers');
+
+async function detectPII(text) {
+    // Load tokenizer
+    const tokenizer = await AutoTokenizer.from_pretrained('path/to/model');
+    
+    // Load ONNX model
+    const session = await ort.InferenceSession.create('onnx/model.onnx');
+    
+    // Tokenize input
+    const inputs = await tokenizer(text, { 
+        padding: true, 
+        truncation: true, 
+        return_tensors: 'ortvalue' 
+    });
+    
+    // Run inference
+    const outputs = await session.run(inputs);
+    
+    // Process outputs
+    const logits = outputs.logits;
+    // ... process predictions
+}
+```
+
+## Model Architecture
+
+- **Architecture:** BertForTokenClassification
+- **Hidden Size:** 768
+- **Intermediate Size:** 3072
+- **Attention Heads:** 12 (typical for BERT-base)
+- **Hidden Layers:** 12 (typical for BERT-base)
+- **Activation Function:** GELU
+- **Max Sequence Length:** 512 tokens
+- **Dropout:** 0.1
+- **Number of Labels:** 55 (54 PII labels + Outside)
+
+## Training Details
+
+### Training Data
+
+The model was fine-tuned on the **ai4privacy/pii-masking-300k** dataset:
+- **Dataset:** [ai4privacy/pii-masking-300k](https://huggingface.co/datasets/ai4privacy/pii-masking-300k)
+- **Size:** 300,000 examples
+- **Format:** Pre-annotated text with BIO labels for PII entities
+- **License:** Check dataset page for license details
+
+### Training Procedure
+
+- **Base Model:** `bert-base-uncased` (Google BERT)
+- **Tokenization:** WordPiece tokenization with lowercase normalization
+- **Max Sequence Length:** 128 tokens (optimized for efficiency)
+- **Padding Token:** [PAD] (ID: 0)
+- **Unknown Token:** [UNK] (ID: 100)
+- **CLS Token:** [CLS] (ID: 101)
+- **SEP Token:** [SEP] (ID: 102)
+- **Mask Token:** [MASK] (ID: 103)
+
+### Training Hyperparameters
+
+- **Learning Rate:** 2e-5
+- **Batch Size:** 16 (per device)
+- **Number of Epochs:** 3
+- **Weight Decay:** 0.01
+- **Optimizer:** AdamW (default)
+- **Training Platform:** Kaggle with GPU T4 x2
+- **Training Time:** ~1-2 hours
+
+### Evaluation Strategy
+
+- **Evaluation Metric:** SeqEval (standard for NER tasks)
+- **Evaluation Strategy:** Every epoch
+- **Metrics Tracked:**
+  - Precision
+  - Recall
+  - F1 Score
+  - Accuracy
+
+## Evaluation
+
+The model should be evaluated on appropriate PII detection benchmarks using standard NER metrics (F1, Precision, Recall) for each entity type.
+
+## Limitations and Bias
+
+- The model's performance may vary across different text domains and writing styles
+- May not generalize well to PII formats from countries/regions not well-represented in training data
+- Context-dependent entities (e.g., names that are also common words) may be challenging
+- The model may have biases present in the training data
+- Should not be used as the sole method for PII detection in critical applications without human review
+
+## Ethical Considerations
+
+This model is designed to help protect privacy by detecting PII in text. However:
+
+- The model is not perfect and may miss some PII (false negatives) or incorrectly flag non-PII (false positives)
+- Should be used as part of a comprehensive privacy protection strategy
+- Users should be aware of applicable privacy regulations (GDPR, CCPA, etc.)
+- The model's use should comply with all relevant laws and regulations
+- Consider the implications of automated PII detection in your specific use case
+
+## ONNX Runtime Compatibility
+
+This model is compatible with ONNX Runtime and can be deployed on:
+- CPU (optimized for inference)
+- GPU (CUDA)
+- Edge devices
+- Web browsers (via ONNX.js)
+- Mobile devices (iOS/Android)
+
+## File Structure
+
+```
+.
+├── README.md                    # This file
+├── config.json                  # Model configuration
+├── tokenizer_config.json        # Tokenizer configuration
+├── tokenizer.json              # Fast tokenizer
+├── vocab.txt                   # Vocabulary file
+├── special_tokens_map.json     # Special tokens mapping
+└── onnx/
+    └── model.onnx              # ONNX model file
+```
+
+## Citation
+
+If you use this model in your research or application, please cite:
+
+```bibtex
+@misc{bert-pii-onnx,
+  title={BERT PII Detection Model (ONNX)},
+  author={Your Name/Organization},
+  year={2025},
+  howpublished={\url{https://huggingface.co/your-username/bert-pii-onnx}}
+}
+```
+
+### Base Model Citation
+
+This model is based on BERT. Please also cite the original BERT paper:
+
+```bibtex
+@article{devlin2018bert,
+  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
+  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
+  journal={arXiv preprint arXiv:1810.04805},
+  year={2018}
+}
+```
+
+## Contact
+
+For questions, issues, or feedback about this model, please open an issue in the model repository.
+
+## Acknowledgments
+
+### Base Model
+This model is built upon **BERT (Bidirectional Encoder Representations from Transformers)** developed by Google Research:
+- Original BERT paper: [Devlin et al., 2018](https://arxiv.org/abs/1810.04805)
+- BERT is licensed under Apache 2.0
+
+### Dataset
+The model was trained on **ai4privacy/pii-masking-300k**:
+- Dataset: [ai4privacy/pii-masking-300k](https://huggingface.co/datasets/ai4privacy/pii-masking-300k)
+- Creator: ai4privacy team on Hugging Face
+- Size: 300,000 examples with PII annotations
+- Please cite the dataset creators if you use this model
+
+```bibtex
+@misc{ai4privacy-pii-dataset,
+  title={PII Masking 300K Dataset},
+  author={ai4privacy},
+  year={2024},
+  howpublished={\url{https://huggingface.co/datasets/ai4privacy/pii-masking-300k}}
+}
+```
+
+### Technologies
+- **Transformers Library**: [Hugging Face](https://github.com/huggingface/transformers)
+- **ONNX**: [Open Neural Network Exchange](https://onnx.ai/) for cross-platform model deployment
+- **ONNX Runtime**: [Microsoft ONNX Runtime](https://onnxruntime.ai/) for efficient inference
+
+### Special Thanks
+- Hugging Face team for the Transformers library and model hub infrastructure
+- ONNX community for standardized model format and runtime
+- Contributors to the training dataset (if applicable)

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
+}

onnx/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]"
+}