GGUF quantizations of Jackrong/Qwopus3.6-35B-A3B-v1 for use with llama.cpp and compatible runtimes. > 📎 Vision support: Place mmproj.gguf in the same directory as the main .gguf file to enable visual capabilities. Fine-tuning used LoRA with ~9% of model parameters participating in updates. Training followed a three-stage curriculum: Stage 1 — Format Establishment: Short-to-medium length, format-stable reasoning samples to establish structured output. Stage 2 — Complexity Scaling & Multi-Teacher Distillation: Gradually increasing proportion of complex reasoning samples distilled from a 27B teacher model. Stage 3 — Long-Context Reinforcement & Anti-Drift: Long-context reasoning with 10% short sample replay to prevent catastrophic forgetting. For partial GPU offloading use -ngl to fit within available VRAM.
Модальности:
Генерация текста Компьютерное зрение Мультимодальность
Области применения:
Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: barozp
Теги: gguf, quantized, llama.cpp, qwen3_5_moe, mixture-of-experts, reasoning, multimodal, vision
Лайков: 3 | Загрузок: 481
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
