!image This repository contains a surgically de-censored version of Openbmb’s MiniCPM5 1B model, optimized via weight abliteration techniques. By applying the heretic framework across an extensive 2000-trial search space, we successfully isolated and neutralized the primary refusal vectors embedded within the attn.oproj and mlp.downproj layers. — Optimal Balance: Selected Trial 126 out of 2000 iterations for the perfect trade-off between freedom and reasoning capabilities. — Refusal Rate: Dropped down to 3/100 (from the original near-total refusal on safety benchmarks). — KL Divergence: 0.0361 — Demonstrates that general language capabilities are preserved relative to the original model. However, safety-aligned weights in attn.oproj and mlp.downproj have been surgically removed; this is intentional modification, not unintended degradation. We believe in radical transparency. Instead of just claiming «uncensored», we evaluated both the vanilla model and our Heretic variant side-by-side: Unlike aggressive fine-tuning which often degrades the model’s core logic or shifts its grammar distributions, this weight manipulation directly zeros out the activation steering directions that…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: K0D3IN
Теги: llama, minicpm5, heretic, abliteration, mit, decensored, conversational, en
Лайков: 4 | Загрузок: 298
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
