This is the 3-bit Apple MLX release of an abliterated version of MiniMaxAI’s MiniMax-M2.7. By applying Heretic’s Ablated Refusal Adaptation (ARA), the base refusal behavior was removed at the weight level. The result keeps MiniMax-M2.7’s sparse MoE reasoning, long-context instruction following, and general capability profile, but no longer defaults to the original refusal pattern. This build uses layer-aware mixed 3/4-bit MLX quantization. The bulk of the model is quantized to 3-bit, while sensitive projection and output modules are kept at 4-bit treatment for better stability. — Format: MLX safetensors — Effective quantization: 3.683 bits per weight — Runtime: mlx-lm — Source checkpoint: Youssofal/MiniMax-M2.7-abliterated-BF16 MiniMax-M2.7 is a 229B sparse MoE model with 10B active parameters per token, 62 layers, hybrid attention, 256 local experts with 8 active per token, and a 200K context window. This release was produced with a direct Heretic ARA run using the fixed parameter set below: — startlayerindex = 30 — endlayerindex = 51 — preservegoodbehaviorweight = 0.4512 — steerbadbehaviorweight = 0.0037 — overcorrectrelativeweight = 0.8804 — neighborcount = 14` — Official…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Youssofal
Теги: mlx, minimax_m2, mlx-lm, minimax, moe, mixture-of-experts, abliterated, uncensored
Лайков: 4 | Загрузок: 120
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.