Disclaimer on MLX Patcher — Provided as-is, no warranty of any kind. Read the code before running — it modifies installed packages in place. — concerns: gemma4mlxpatch.py and PATCH-README.md provided alongside the model Note on MLX support: The MLX conversion of this model does not load with stock mlx-lm / mlx-vlm as released. This is not a defect of the quantization itself — it’s a gap in the upstream loaders for this checkpoint’s two layout quirks: 1. The checkpoint ships a separate output layer (lm_head). The unpatched mlx-vlm language model has no head module at all (tied embeddings hard-wired) and the unpatched mlx-lm remaps the head key to the wrong module path, so strict loading aborts. 2. A few attention layers use different dimensions than the rest of the model (described in a sparse per-layer section of the config). The unpatched loaders silently drop that section and build those layers with the wrong shape, which crashes the weight check.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: McG-221
Теги: mlx, gemma4, conversational, en, 8-bit
Лайков: 3 | Загрузок: 135
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.