GLM-4.5-Air-Derestricted is a Derestricted version of GLM-4.5-Air, created by Arli AI. Our goal with this release is to provide a version of the model that removed refusal behaviors while maintaining the high-performance reasoning of the original GLM-4.5-Air. This is unlike regular abliteration which often inadvertently «lobotomizes» the model. To achieve this, Arli AI utilized Norm-Preserving Biprojected Abliteration, a refined technique pioneered by Jim Lai (grimjim). You can read the full technical breakdown in this article. Standard abliteration works by simply subtracting a «refusal vector» from the model’s weights. While this works to uncensor a model, it is mathematically unprincipled. It alters the magnitude (or «loudness») of the neurons, destroying the delicate feature norms the model learned during training. This damage is why many uncensored models suffer from degraded logic or hallucinations. This model was modified using a three-step approach that removes refusals without breaking the model’s brain: 1. Biprojection (Targeting): We refined the refusal direction to ensure it is mathematically orthogonal to «harmless» directions. This ensures that when we cut out the…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: cyankiwi
Теги: glm4_moe, abliterated, derestricted, glm-4.5-air, unlimited, uncensored, conversational, endpoints_compatible
Лайков: 3 | Загрузок: 33
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
