heretic
Heretic automatically strips the built-in refusals out of open-weight AI models, co-minimizing refusals and quality loss, with no fine-tuning or knowledge of model internals required.
View p-e-w/heretic on GitHub- GitHub stars
- 40,523
- Forks
- —
- Language
- Python
Project details
- Repository
- p-e-w/heretic
- Licence
- AGPL-3.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Explore by topic
More tools in Models & training
- transformers
huggingface · Apache-2.0
The open-source library that provides ready-to-use implementations of virtually every major AI model for text, vision, audio, and multimodal use, letting developers run…
- vllm
vllm-project · Apache-2.0
vLLM is an open-source engine that runs large language models fast and cheaply in production, used widely to self-host models like Llama, Qwen and DeepSeek.
- kimi-k3-in-c
fareedkhan-dev · Apache-2.0
Lets a 2.78-trillion-parameter AI model run inference on a regular laptop with no GPU and just 8GB of RAM, by rewriting the whole inference engine in dependency-free C.
- unsloth
unslothai · Apache-2.0
A free local app for running and training your own AI language and image models on your own machine.