HikmaAI/hikmaai-distilbert-pii

HikmaAI DistilBERT PII NER

A fine-tuned DistilBERT model for Named Entity Recognition (NER) of Personally Identifiable Information (PII) in multilingual text. Trained on 6 languages (English, Italian, French, German, Spanish, Dutch). Detects 17 entity types across personal, financial, and contact information categories.

Model Details

Property	Value
Base model	distilbert-base-uncased
Task	Token classification (BIO tagging)
Entity types	17 (35 labels: B- and I- for each + O)
Parameters	~66M
ONNX INT8 size	129 MB
Max sequence length	512
Input tensors	input_ids, attention_mask
Output	logits shape [batch, seq_len, 35]
License	Apache 2.0

Entity Types

Category	Entity	Label	Examples
Personal	Given name	GIVENNAME	John, Maria, Ahmed
	Surname	SURNAME	Smith, Garcia, Chen
	Date of birth	DATEOFBIRTH	1990-01-15, 15/03/1985
	Username	USERNAME	john_doe, user123
	Password	PASSWORD	P@ssw0rd!, mySecret
Contact	Email	EMAIL	john@example.com
	Phone	TELEPHONENUM	+1-555-0123, 06 12345678
	Street	STREET	123 Main St, Via Roma 42
	City	CITY	New York, London, Milano
	ZIP code	ZIPCODE	10001, SW1A 1AA
	Building number	BUILDINGNUM	Apt 4B, Suite 200
Financial	Credit card	CREDITCARDNUMBER	4111-1111-1111-1111
	Account number	ACCOUNTNUM	GB29 NWBK 6016 1331 9268 19
	Tax number	TAXNUM	SSN, TIN, codice fiscale
Identity	Social security	SOCIALNUM	123-45-6789
	Driver license	DRIVERLICENSENUM	D1234567
	ID card	IDCARDNUM	National ID numbers

Usage

Transformers

from transformers import pipeline

ner = pipeline(
    "ner",
    model="hikmaai-io/hikmaai-distilbert-pii",
    aggregation_strategy="simple"
)

results = ner("Contact John Smith at john@example.com or call +1-555-0123")
for entity in results:
    print(f"{entity['word']:20s} -> {entity['entity_group']:20s} ({entity['score']:.2f})")

ONNX Runtime

import onnxruntime as ort
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("hikmaai-io/hikmaai-distilbert-pii")
session = ort.InferenceSession("onnx/model_quantized.onnx")

inputs = tokenizer("Contact John Smith at john@example.com", return_tensors="np")
outputs = session.run(None, {
    "input_ids": inputs["input_ids"],
    "attention_mask": inputs["attention_mask"],
})
# outputs[0] shape: [1, seq_len, 35] (logits for 35 BIO labels)

ONNX Runtime (Go)

The model is designed for high-performance inference in Go applications via yalue/onnxruntime_go:

// 2 input tensors: input_ids, attention_mask
// Output: logits [1, seq_len, 35]
// Post-processing: argmax per token -> BIO label -> entity spans

Training

• Base model: distilbert-base-uncased
• Dataset: ai4privacy/pii-masking-400k (325K annotated examples, 6 languages: EN 21%, IT 20%, FR 20%, DE 20%, ES 10%, NL 10%)
• Checkpoints: 15,000 steps
• Quantization: INT8 dynamic quantization via ONNX Runtime (FP32 also available)

File Structure

├── config.json              # Model configuration
├── model.safetensors        # FP32 weights (PyTorch/safetensors)
├── tokenizer.json           # Fast tokenizer
├── tokenizer_config.json    # Tokenizer configuration
├── onnx/
│   ├── model.onnx           # FP32 ONNX
│   └── model_quantized.onnx # INT8 ONNX (recommended for inference)

Privacy Design

This model is designed for privacy-preserving PII detection in AI security gateways:

• Detection only: the model identifies entity spans and types. It does not store, transmit, or log the actual PII values
• Counts, not content: downstream systems receive entity type counts (e.g., {"EMAIL": 2, "PHONE": 1}), never the detected text
• Local inference: runs entirely on-device via ONNX Runtime, no external API calls
• Stateless: no request data is retained between inferences

Limitations

• Trained on 6 languages (EN, IT, FR, DE, ES, NL); performance on other languages is untested
• Maximum sequence length: 512 tokens (longer texts require chunking)
• Regex-based PII detection (emails, phone numbers, credit cards) may outperform NER for well-structured patterns; this model adds value for unstructured PII (names, addresses, free-text credentials)
• INT8 quantization may slightly reduce accuracy on edge cases compared to FP32

Citation

@misc{hikmaai-distilbert-pii,
  author = {HikmaAI},
  title = {HikmaAI DistilBERT PII NER: Fine-tuned model for PII detection in AI security gateways},
  year = {2026},
  url = {https://huggingface.co/hikmaai-io/hikmaai-distilbert-pii}
}