INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED BUT SOME MAY HAVE NO CONTENT > [!TIP] > VRAM at 6.0 bpw: weights on disk + ~2 GB context overhead. Best on 32 GB+ cards (V100, A100, RTX 6000) where there’s room for long context. Quantization recipe (advanced — embedded in quantization_config.json) Loaded automatically by every ExLlamaV3 loader; reproduced here for searchability. > [!IMPORTANT] > Use and license follow the base model. > Quantization adds no additional restrictions. Refer to the upstream repository for terms, citation, and safety documentation. Quantized with BlockQuant · convention {org}/{model}-exl3-{bpw}bpw
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: blockblockblock
Теги: exllamav3, qwen3_5_moe, exl3, quantized, mixture-of-experts, qwen, conversational, 6-bit
Лайков: 3 | Загрузок: 34
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
