Quantized GGUF builds of Aleph-Alpha/Kolibri-1 — Aleph Alpha’s 78.10B-parameter (3.46B active) German/English MoE reasoning model — converted from the FP8 release at revision e52eb4627d11516b0c01de49210ab5a4e4061444 with DwarfStar’s kolibri1quantize.py`. The weights are modified (quantized) relative to the original release. > [!IMPORTANT] > These are DwarfStar (ds4) format GGUFs. They load with the ds4 > inference engine (Metal or CPU reference) and are not generic > llama.cpp-compatible GGUF files. Suggested order of preference: Q8 (closest to the release, ~78 GB of weights), Q4 (good quality/size trade-off), Q2 (smallest; quantized with the weight-energy bootstrap since no imatrix was used). Kolibri-1 support is not merged upstream yet; it lives in the main branch of aparusel/ds4-kolibri-1 for now. Build that fork and point it at a file: Kolibri-1 runs on Metal and the CPU reference backend (ds4 —cpu -m …). CUDA, ROCm, tensor/pipeline parallelism, SSD streaming, speculation and vision are not supported for this model. Thinking is on by default; —think-level N maps to the released low/medium/high effort wording, and the model defaults to temperature 1, top-p 0.97, top-k 128.…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: aparusel
Теги: ds4, gguf, kolibri, moe, reasoning, tool-calling, dwarfstar, de
Лайков: 3 | Загрузок: 903
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
