Fully automatic censorship removal for language models
docs: update README
Philipp Emanuel Weidmann11790139999f
diff --git a/README.md b/README.mdindex 5990978..b07825e 100644--- a/README.md+++ b/README.md@@ -1,6 +1,6 @@<img width="128" height="128" align="right" alt="Logo" src="https://github.com/user-attachments/assets/df5f2840-2f92-4991-aa57-252747d7182e" />-# Heretic: Fully automatic censorship removal for language models<br><br>[](https://discord.gg/gdXc48gSyT)+# Heretic: Fully automatic censorship removal for language models<br><br>[](https://discord.gg/gdXc48gSyT) [](https://huggingface.co/heretic-org)Heretic is a tool that removes censorship (aka "safety alignment") fromtransformer-based language models without expensive post-training.@@ -67,8 +67,11 @@ Heretic supports most dense models, including many multimodal models, andseveral different MoE architectures. It does not yet support SSMs/hybrid models,models with inhomogeneous layers, and certain novel attention systems.-You can find a collection of models that have been decensored using Heretic-[on Hugging Face](https://huggingface.co/collections/p-e-w/the-bestiary).+You can find a small collection of models that have been decensored using Heretic+[on Hugging Face](https://huggingface.co/collections/p-e-w/the-bestiary),+and the community has created and published+[well over 1,000](https://huggingface.co/models?other=heretic)+Heretic models in addition to those.## Usage