Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
132,241 visible repositories in the index
1–12 of 12 · Most stars
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
OBLITERATE THE CHAINS THAT BIND YOU
Get your own Bitcoin & Lightning Node running - on a RaspberryPi with a nice LCD
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Spreading Thankfulness in Open Source.
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
This is a study aim to transfer the single concept by using DIT model self-attention capablity
create a secondary jailbroken iOS on iPhone 11 series devices using usbliter8.
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
Get your own Bitcoin & Lightning Node running - on a RaspberryPi with a nice LCD
♟︎ Update a pinned gist to contain your Chess.com Blitz, Bullet, Rapid, Puzzles & Daily Ratings