annihilate-llm is an AGPL-3.0-or-later Python package for automatically removing censorship behavior from language models. It uses abliteration techniques with transformer-based models and runs locally for developers and researchers.
annihilate-llm sits in PulseGate's Quantised & converted weights category. It focuses on removing censorship behavior from language models without manually applying abliteration techniques. It is built as an open-source project for AI developers and machine-learning researchers. The project is open source (AGPL-3.0). It runs on the command line, and it can be self-hosted.
It is developed by tjcrims0nx, and it first shipped in 2026. Development happens publicly on GitHub with 40 stars and 189 commits in the last 90 days. Key capabilities include censorship removal, LLM abliteration, and transformer support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do