tjcrims0nx/annihilation-llm

Fully automatic censorship removal for language models

The production engine for directional ablation. Unalign / remove models censorship efficiently on any hardware.

Make abliterated models with transformers, easy and fast

Abliterates models quickly and efficently, Qwen2.5-7B: 95%→2% refusal at 0.095 KL

OBLITERATE THE CHAINS THAT BIND YOU

llama.cpp fork that abliterates at inference

Reproduction code for "A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models"

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.