heretic

<div align="center">

<img width="128" alt="Heretic logo" src="https://github.com/user-attachments/assets/df5f2840-2f92-4991-aa57-252747d7182e" />

# Heretic

### Training-free language model modification

**Remove censorship**, suppress slop, reduce sycophancy, and more.<br>
All in an afternoon, on your gaming PC.

[![Discord](https://img.shields.io/discord/1447831134212984903?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=for-the-badge)](https://discord.gg/gdXc48gSyT)&nbsp;&nbsp;&nbsp;&nbsp;
[![Matrix](https://img.shields.io/badge/Matrix-black?logo=matrix&style=for-the-badge)](https://matrix.to/#/#heretic:matrix.org)&nbsp;&nbsp;&nbsp;
[![Follow us on Hugging Face](https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-md-dark.svg)](https://huggingface.co/heretic-org)&nbsp;&nbsp;&nbsp;
[![Codeberg mirror](https://img.shields.io/badge/Codeberg%20mirror-black?logo=codeberg&style=for-the-badge)](https://codeberg.org/p-e-w/heretic)

</div>

-----

&nbsp;

[![#1 Repository of the Day](https://trendshift.io/api/badge/repositories/20538)](https://trendshift.io/repositories/20538)&nbsp;&nbsp;&nbsp;&nbsp;
[![Model and download statistics](https://github.com/user-attachments/assets/c9b5a660-7ef9-43c7-991c-fd9d63ea8bd8)](https://heretic.sdad.pro/)


## Modify any LLM that you can run on your hardware[^1]

[^1]: Heretic supports on-the-fly 4-bit model quantization with bitsandbytes,
which can reduce the amount of VRAM required to process a model to the same amount
that is used to run a typical quantized version of it, at a slight accuracy cost.
Set the `quantization` option to `bnb_4bit` to enable this.

Heretic is a unique tool that lets you do what only corporations with access
to massive computing power usually do: *Modify,* rather than merely run,
language models. It does not perform expensive training; rather, it uses
a collection of mathematical techniques to steer behavior based on contrasting
example prompts and matching scorers.

Heretic can, depending on the configuration:

* **Suppress refusals/remove censorship** (this is the [default action](/config.default.toml))
* Reduce slop ([`config.noslop.toml`](/config.noslop.toml))
* Reduce humor ([`config.nohumor.toml`](/config.nohumor.toml))
* Reduce sycophancy ([`config.nosyco.toml`](/config.nosyco.toml))
* Alter emotional alignment ([`config.emotions.toml`](/config.emotions.toml))
* Shorten response length ([`config.terse.toml`](/config.terse.toml))

and many, many other things.

### :bangbang: Using Heretic does NOT require understanding how language models work internally :bangbang:

In fact, you can go from zero to removing censorship from your first model
[in a matter of seconds](#usage). Heretic supports most dense models, including
many multimodal models, several different MoE architectures, and many modern
hybrid models.

The community has created and published
[thousands](https://huggingface.co/models?other=heretic)
of models with Here