Small Language Model Inference, Fine-Tuning and Observability.
-
Updated
Apr 11, 2026 - Python
Small Language Model Inference, Fine-Tuning and Observability.
Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.
Deidentify people's names and gender specific pronouns
Text preprocessing and PII anonymisation for NLP/ML. ONNX NER ensemble, language detection, stopword removal. Built for statistical ML and language models.
This repository contains the code and data for the text re-identification attack presented in B. Manzanares-Salor, D. Sánchez, P. Lison, Evaluating the disclosure risk of anonymized documents via a machine learning-based re-identification attack, Data Mining and Knowledge Discovery, 2024.
Simple project on html anonymization
This repository contains the code and data for the text anonymization enhancement method presented in B. Manzanares-Salor, D. Sánchez, Enhancing text anonymization via re-identification risk-based explainability, Submitted, 2024.
Shape-matched text anonymization for Raycast — a humane alternative to Lorem Ipsum.
This repository contains the code and experimental data for the Text Anonymization Evaluator (TAE), an evaluation tool for anonymized documents including multiple state-of-the-art metrics for both utility preservation and privacy protection assessment.
The gate between your sensitive documents and the AI you want to use. It redacts names into reversible surrogates, then attacks its own redaction with a real GPT-5.6 adversary and rules whether it held: clearing what survives, refusing what does not, restoring real names locally. Only sanitized text ever leaves your machine.
🛡️ Text Anonymizer using NuNER Zero-shot An academic project that auto-detects & masks sensitive entities (names, orgs, locations) in .txt/.docx files using Zero-shot NER. Features CLI & REST API. Replaces data with realistic fakes (Faker) or [REDACTED]. Built with Python, Flask, GLiNER.
Anonymizer2 is a Python library for text anonymization that uses LangExtract to recognize and replace entities, with a FastAPI web API for integration.
Add a description, image, and links to the text-anonymization topic page so that developers can more easily learn about it.
To associate your repository with the text-anonymization topic, visit your repo's landing page and select "manage topics."