SLMs for semantically similar replacement of PII to provide better end-user privacy. The Anonymizer-0.6B is a lightweight privacy-preserving language model trained for surgical anonymization of personal data before queries leave your device. It detects and replaces sensitive information (names, companies, identifiers, financials, etc.) with semantically similar alternatives, while preserving query intent and meaning. This 0.6B model is optimized for latency and mobile use, making it a good fit as a speculative decoder or lightweight anonymizer inside the Enchanted app. Larger variants (1.7B / 4B) deliver stronger anonymization accuracy, but 0.6B runs fastest on consumer hardware. Primary use: Running inside the Eternis app to protect user queries before they are sent to larger LLMs. Secondary use: Standalone anonymizer model for research or integration into other privacy-preserving workflows. Good for: Detecting and replacing PII while leaving public knowledge intact. Not for: General-purpose generation. Base: Qwen3-0.6B. Data: ~30k samples covering PII replacement + non-replacement categories. Method: Supervised fine-tuning → GRPO with GPT-4.1 as judge. Latency: Performs…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: eternisai
Теги: qwen3, conversational, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 58
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
