This is an MLX release of an abliterated, uncensored version of Qwen’s Qwen3.6-27B with the source image/video payload retained, made from the published BF16 checkpoint. By applying a Heretic-style MPOA pipeline with magnitude preservation on the Qwen3.6-27B dense text stack, the base refusal behavior was removed at the weight level. This MLX build keeps that text-side behavior in Apple Silicon format while retaining Qwen3.6-27B’s vision/video payload in the repo. Qwen3.6-27B is a 27.8B dense vision-language model with 64 text layers, hybrid linear/full attention (3 linear-attention + 1 full-attention per 4-layer group), and an integrated image + video vision tower. This MLX variant was built directly from Youssofal/Qwen3.6-27B-Abliterated-Heretic-Uncensored-BF16 using dynamic layer-aware 6-bit affine MLX quantization with 64/32 group-size tiers. It is a dynamic, layer-aware quantization pass rather than a flat conversion. The retained multimodal payload includes the source vision/video tensors and processor files; direct image/video use depends on MLX runtime support for Qwen3.6 multimodal inputs. — model-.safetensors: quantized MLX text weights -…
Модальности:
Генерация текста Компьютерное зрение Мультимодальность
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Youssofal
Теги: mlx, qwen3_5, mlx-lm, qwen, qwen3.6, dense, multimodal, vlm
Лайков: 3 | Загрузок: 215
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
