This model is a fully fine-tuned version of Qwen/Qwen3-8B on the WNT3D/Ultimate-Offensive-Red-Team dataset. !Screenshot 2026-01-05 at 5.31.24 PM vLLM deployment shown above + custom web gui (coming soon) — Red-team simulation and research — Security training and tabletop exercises — Adversarial LLM evaluation — Controlled internal testing environments — Studying failure modes of aligned models — learningrate: 1.5e-05 — trainbatchsize: 4 — evalbatchsize: 4 — seed: 42 — distributedtype: multi-GPU — numdevices: 4 — gradientaccumulationsteps: 2 — totaltrainbatchsize: 32 — totalevalbatc
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: MrPibb
Теги: qwen3, generated_from_trainer, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 23
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
