Calibrated 3-bit MLX quantization of poolside/Laguna-S-2.1 (118B total, 8B activated per token), produced with oMLX oQ at level 3 enhanced — 3.59 bits/weight effective, 49 GB on disk. Data-driven mixed precision: bits are allocated per tensor from an imatrix-calibrated sensitivity map, not a fixed rule. For Apple Silicon. 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 Until it lands, use mlx-vlm (0.6.3+), which implements laguna as a text-only model: oMLX serves it directly from 0.5.3 on — it vendors that PR and patches it into mlx-lm at import, so no model setting is needed. On earlier builds, discovery decides between the mlx-lm and mlx-vlm loaders by looking for a vision sub-config, and laguna has none — so it lands on mlx-lm and fails with Model type laguna not supported. Set…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: mlx-community
Теги: mlx, laguna, oq, quantized, moe, conversational, custom_code, 3-bit
Лайков: 4 | Загрузок: 281
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
