Back to directory

rizzo-pii

rizzo-pii is a small, CPU-friendly model that detects 22 categories of personal data in Italian legal text, including Italian tax and property identifiers, and drives a local, reversible anonymize-then-restore workflow so sensitive documents can still be sent to a cloud LLM.

Visit website (opens in a new tab)rizzo-ai-academy.github.io
rizzo-pii

rizzo-pii is a local, reversible anonymization tool for Italian legal text. Its core model, rizzo-pii:0.3B, is a roughly 0.3-billion-parameter, CPU-friendly token-classification model built on an mmBERT and ModernBERT backbone that detects 22 categories of personal data, including Italian-specific legal identifiers such as the tax code, VAT number and land-registry data.

The workflow anonymizes a document locally, replaces detected identifiers with placeholders tracked in a reversible local dictionary, sends only the placeholders to a frontier LLM such as ChatGPT, Claude or Gemini, and restores the real values locally afterward, so the underlying data never leaves the user's device. It targets law firms, accountants, notaries and others bound by the GDPR, and installs from a Windows installer, a macOS build for Apple Silicon, or a Linux AppImage.

More in Models

See all 405
  • mini-AGI

    github.com

    A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.

  • An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.

  • peekaboolean

    github.com

    A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.