!MMLU-Pro !GSM8K !GPQA !Uncensored All the capability, none of the refusals. > Uncensored at no cost to quality. Removing refusals left capability fully intact: it matches the aligned model on MMLU-Pro (88.29%), GSM8K, and hard GPQA-Diamond reasoning (56.57% vs base 57.58%, within noise) — and still beats the base on knowledge. — Unrestricted — refusal behavior removed; declines far fewer requests — Top-tier knowledge — 88.29% MMLU-Pro, above the base, with zero abliteration tax — Strong math — 97.67% GSM8K — Agentic tool-calling + step-by-step reasoning This model has had refusal behavior reduced, so it may produce content a safety-tuned model would decline. You are responsible for how you use it — use it lawfully and ethically, in accordance with the base-model and dataset licenses. It is not intended for producing harmful, illegal, or abusive content. — Unrestricted, agentic multi-turn tool-calling — Chain-of-thought reasoning — Top-tier general knowledge and math — Multimodal (vision + text) architecture > Tip: this model reasons before answering — give it a generous max_tokens so it can finish its chain of thought.
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: lemuralabs
Теги: qwen3_5, image-text-to-text, agentic, tool-calling, function-calling, reasoning, uncensored, abliterated
Лайков: 4 | Загрузок: 115
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
