AlphaUncommon
wuwangzhang1216/abliterix
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
- Owner
- wuwangzhang1216 (personal account)
- Stars
- Stars: 280
- Forks
- Forks: 46
- Language
- Python
- License
- AGPL-3.0
- Created
- 2026
- Topics
- abliterationdecensoringllmloraoptunapytorchtransformersuncensoredalignmentgemma
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by wuwangzhang1216
All 3 repos by wuwangzhang1216- wuwangzhang1216/congcong-schoolStars: 1,240TypeScriptBeta
- wuwangzhang1216/DirectorSKILLStars: 311Alpha
Nearby in Python
All Python repos- MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-SparksStars: 280PythonAlpha
- sunwenzhe-git/atlasStars: 280PythonAlpha
- developeryj1992/ai-trend-studioStars: 280PythonAlpha
- madisona/django-google-mapsStars: 280PythonAlpha
- posativ/acrylamidStars: 280PythonAlpha
- robertkrimen/gist-itStars: 280PythonAlpha