zaakir.io | blog

My thoughts

Tag: abliteration

Abliteration: Uncensoring an LLM (and Why You Might Want To)

Commercial models refuse a lot of legitimate requests. Here's why "uncensoring" an open-weight model is useful and how I achieved it. ⚠️ A note before we start. An uncensored model will answer almost...

LLMs, AI, abliteration, local ai