josepha-mayo/model-unfetter

Fully automatic censorship removal for language models

Autonomous Language Model Decensoring Framework

Make abliterated models with transformers, easy and fast

OBLITERATE THE CHAINS THAT BIND YOU

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

llama.cpp fork that abliterates at inference

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

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

Comparative forensic analysis of LLM abliteration techniques