Embeds secret identifiers into LLMs to prove ownership and prevent unauthorized use.
This repo provides tools to fine-tune LLMs, embedding unique query-response fingerprints. By running `python -m oml.fingerprinter --help`, you can generate and apply these verifiable AI signatures.
Embeds secret identifiers into LLMs to prove ownership and prevent unauthorized use.
AI model developers and owners looking to protect their intellectual property.
Not enough data yet. Star history will appear after a few days of tracking.
OML Overview | OML Whitepaper | Sentient Foundation
Welcome to OML 1.0: Fingerprinting. This repository houses the tooling for generating and embedding secret fingerprints into LLMs through fine-tuning to enable identification of LLM ownership and protection against unauthorized use.