This repository contains GGUF quantized versions of Jais-2-70B-Chat for use with llama.cpp and compatible inference engines. — Recommended format: Q4KM for best quality/size tradeoff — K-quant variants (Q3KM, Q4KM, Q5KM): Require -b 8 flag when using GPU offloading ———|————————|—————————-|————————|—————————-| ———|—————-|————-|—————|————-|————-|———|————— | Overall, our results show that: — Jais-2-70B delivers competitive Arabic and English instruction-following per — Jais-2-70B achieves the highest scores across nearly all AraGen metrics, outperforming Qwen2.5-72B and Llama-3.3-70B on Arabic generative tasks. — Academics: Researchers focusing on Arabic NLP, multilingual modeling, or cultural alignment — Businesses: Companies targeting Arabic-speaking markets — Developers and ML Engineers: Integrating Arabic language capabilities into applications and workflows — Research: — Natural language understanding and generation tasks — Conducting interpretability or cross-lingual alignment analyses — Investigating Arabic…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: inception42
Теги: gguf, llama.cpp, ar, en, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 56
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
