Independent GGUF conversion and quantization of Aleph Alpha’s Kolibri-1. Aleph Alpha created the original model; Prompt48 produced these GGUF artifacts from the original checkpoint. No further training was performed. These files require Kolibri architecture support. This release uses llama.cpp at 836d57176 with the Kolibri patch by Hob-forge/Seraphiel102, credited and available at Hob-forge/Kolibri-1-GGUF. Ordinary llama.cpp, Ollama and LM Studio builds without that support cannot load these files. The implementation patch is MIT; the original model weights are Apache-2.0. The original model license is included with this release. The source is Aleph Alpha’s block-scaled FP8 checkpoint, converted to a BF16 GGUF intermediate. Dequantizing to BF16 does not recover precision lost in the original FP8 checkpoint. Every quantization is generated directly from that intermediate, rather than from another low-bit quantization. Validation on this release: CPU-only patched llama.cpp, 4,096-token configured context; four short prompts. — english (2.0 seconds, including prompt processing): Sunlight is made of many colors, and shorter blue wavelengths scatter more easily in the atmosphere. This…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Prompt48
Теги: gguf, llama.cpp, kolibri1, mixture-of-experts, en, de, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 376
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.