distributedcognition/Hemmingway-1-27B-abliterated - Каталог нейросетей
Генерация текста

distributedcognition/Hemmingway-1-27B-abliterated

Добавлено:
distributedcognition/Hemmingway-1-27B-abliterated

This is an uncensored research model. Its built-in refusals were removed, so it answers prompts the base model declines, including chemical and biological synthesis, cybercrime, weapons, harassment, and fraud. Use it for red-teaming, offensive-security research, and refusal-rate evaluation. It has no guardrails of its own: if you deploy it, add your own input and output moderation (for example Llama Guard). Abliterated variant of Altworld/Hemmingway-1, the creative-writing finetune of Qwen/Qwen3.8-27B (27B, 64 layers, 48 linear attention + 16 full attention, separate MTP draft layer). The refusal direction was removed from the model’s weights with projected writer-level abliteration: per-layer directions fitted as harmful-minus-harmless mean residual states, orthogonalized against the harmless mean direction, then applied as W 0.99, split-half cosine > 0.9). This is the same edit as the runtime GLP projection behind the Bonsai 2 vectors, baked into the weights, which a BF16 dense model allows. The published model is a mirror of the upstream checkpoint with 110 writer tensors replaced (55 layers, all-64 arms kept every writer but measured worse on the quality/compliance curve).…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: distributedcognition
Теги: gguf, qwen3_5_text, abliteration, uncensored, qwen3.8, conversational, endpoints_compatible
Лайков: 3  |  Загрузок: 361

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.