A high-throughput and memory-efficient inference and serving engine for LLMs
其他人工智能更新于 2026-10-25
其他人工智能AGPL-3.0
Repository dossier
p-e-w/heretic
Fully automatic censorship removal for language models
Brief / README 摘要
查看原文Heretic is a tool that removes censorship (aka "safety alignment") from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration" (Arditi et al. 2024, Lai 2025 (1, ), with a TPE-based parameter optimizer powered by Optuna. This approach enables Heretic to work completely automatically. Heretic finds high-quality abliteration parameters by co-minimizing the number of refusals and the KL divergence from the original model. This results in a decensored model that retains as much of the original m…
Topics / 标签
01
浏览全部相关推荐
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
其他人工智能更新于 2026-10-25
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
其他人工智能更新于 2026-10-25
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https://discord.gg/VuxzM8mtf
其他人工智能更新于 2026-10-22
TradingAgents: Multi-Agents LLM Financial Trading Framework
其他人工智能更新于 2026-10-16