GitHub Trending

p-e-w/heretic — Star p-e-w / heretic Fu

29 sec read83 views0 listens

8,720 stars | 869 forks | Python

Star

    p-e-w /

  heretic  


  Fully automatic censorship removal for language models

What it does

Heretic is a tool designed to automatically remove censorship from transformer-based language models, enhancing their performance without extensive retraining. This innovation allows users to create high-quality, uncensored models easily, making it significant for developers and researchers in AI.

Why it matters: Unlock the full potential of AI models with Heretic's automatic censorship removal!

View on GitHub

Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.

You Might Like

GitHub TrendingSep 231 sec read

superlinked/sie — Open-source inference server and production cluster for all the models your agen

2,956 stars | 297 forks | Python Open-source inference server and production cluster for all the models your agent needs. What it does SIE is an open-source inference engine designed to serve multiple machine learning models for agent tasks through a...

Ali Nemati

GitHub TrendingAug 2531 sec read

marin-community/marin — Open-source framework for the research and development of foundation models.

1,898 stars | 184 forks | Python Open-source framework for the research and development of foundation models. What it does Marin is an open-source framework for developing foundation models, focusing on training large language and multimodal models w...

Ali Nemati

GitHub TrendingAug 1537 sec read

huangruiteng/loopx — Lightweight loop engineering state kernel for long-running AI agent teams. Agent

2,454 stars | 139 forks | Python Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence ...

Ali Nemati