wuwangzhang1216/abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

⭐ 207 ⑂ 38 Python AGPL-3.0 · 1 天前推送

abliteration alignment gemma llm lora mixture-of-experts moe peft pytorch transformers uncensored model-editing optuna decensoring

207

Watchers

0

贡献者

0

Commits

0

Releases

16

Open Issues

1 天前

最近推送

原文中文

暂无 README