Skip to content
MoriNoNushi / heretic-ggufView on GitHub
Optuna-optimized "abliteration" (directional ablation) directly on quantized GGUF models via llama.cpp. The base GGUF is never modified — trials run as hot-swapped LoRA adapters, and the result exports as a tiny --lora adapter or a merged GGUF. Supports MoE per-expert ablation.
☆14Aug 9, 2026Updated 3 months ago

Alternatives and similar repositories for heretic-gguf

Users that are interested in heretic-gguf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?