Fanar以阿拉伯语为中心的大型语言模型

Qatar Computing Research Institute (QCRI)1Arabic-Centric Large Language Modelswww.fanar.qaHamad Bin Khalifa UniversityQatar Computing Research Institute (QCRI)Fanar- A National ProjectProject SponsorProject inception and development (30+ scientists and engineers)Technology partners &infrastructure providersCross-Partners Project ManagementPartners Hamad Bin Khalifa UniversityQatar Computing Research Institute (QCRI)Motivation Behind Building FanarPreserve Arabic language and its dialects in the era of AI and LLMsCultural alignment & awareness relevant to 0.5B Arabs & 2.0B MuslimsTechnology ownership & Digital sovereigntyBuilding in-house capacity Content % on the WebHamad Bin Khalifa UniversityQatar Computing Research Institute (QCRI)Fanar Models•A family of highly capable Arabic-centric LLMs−Trained on the largest amount of Arabic content (Over 1.3T cleaned tokens) [40% Arabic, 50% English, 10% code]•Dual Models−Fanar Star: developed full-stack from scratch in-house [7B parame