repoGitHubTrust 82 · PrimaryPublished 7d agoLive · 7d ago
wuwangzhang1216/abliterix
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
