p-e-w/heretic

Autonomous Language Model Decensoring Framework

Make abliterated models with transformers, easy and fast

The production engine for directional ablation. Unalign / remove models censorship efficiently on any hardware.

llama.cpp fork that abliterates at inference

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

OBLITERATE THE CHAINS THAT BIND YOU

The uncensored model library — every uncensored and abliterated model, what it does, free open weights on Hugging Face and hosted API access, in one index. Maintained by RouterHub.

Uncensored vs abliterated AI models — compare exact RouterHub IDs, prices, refusal behavior and cost. DeepSeek, GLM and Qwen, with one API key.

GLM 5.3 Abliterated or Uncensored AI model — 35 jailbreak prompts, model guide and API. One 7API key also covers Claude, GPT, Gemini, Grok, DeepSeek and Kimi.