> ⚠️ Runtime: JANGHT needs a vMLX (Python) build that is not released yet. The bundle was built and validated > on a vMLX development build that adds the JANGT trellis experts (decode and prefill kernels) for this family. > vMLX 1.6.77 and older refuse to load it (they stop with an error; they never produce wrong output). Use it with the first vMLX release that lists JANGHT support. > The previous JANGH2 weights are in this repo’s history at commit > 54fab36 > (revision=»54fab3629aed6b8a2e5e481c3a8885bbe094c820″). Naive-N0.5-Flash for 128 GB Macs: 575 GiB of bf16 weights in 91.31 GiB. 4.6 GiB smaller than our JANGH2 release and closer to the original model: 29% less extra loss on the real next token. A JANGHT bundle of NaiveAI/Naive-N0.5-Flash: a 309B MoE (15.5B active, 256 routed experts, top-8) for coding and agentic work, with a native 1M-token context built from sliding-window attention and sparse attention. Text only. — Routed experts: JANGHT, a per-layer mix of two formats, chosen by measurement: — JANGT: a trellis code at 2, 2.5 or 3 bits per weight (Hadamard-128 rotation, 12-bit state, up to 8 outlier columns per layer kept in fp16). The 2.5-bit variant alternates 6- and…
Модальности:
Генерация текста
Области применения:
Генерация кода Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: JANGQ-AI
Теги: mlx, naive_n05_flash, jang, janght, jangt, jangh, quantized, apple-silicon
Лайков: 3 | Загрузок: 201
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.