SAVRN
Search Contact SAVRN

Independent publisher

Efe Buken

0bserverx

LLMs, Quantization, Fine-tuning, Inference Optimization, Abliteration, Open Source AI

Models in Library1
Datasets in Library0
Models on Hugging Face6
Followers161

Models

RVN is a double-refined abliterated variant of Qwen3.8-27B, built on top of (an ARA abliteration by Tim Rohrbaugh) and further refined with two additional full-weight ARA passes targeting residual refusals. It retains very low behavioral damage (KL ≈ 0.0085) while reducing harmful-prompt refusals from 3/100 (source) to 0–1/100 in independent measurements. ARA (Arbitrary-Rank Ablation) is the abliteration technique implemented in p-e-w/heretic. Traditional directional abliteration finds a single "refusal direction" in activation space and subtracts it — a one-shot, low-rank surgery that is simple but can leave residual refusals or damage unrelated behavior. ARA instead treats abliteration as…

Open weights apache-2.0 transformers