LLaVA ni modeli ya kutambua picha, lugha na uchakataji wa data mseto iliyoundwa na Columbia University, Microsoft Research na University of Wisconsin Madison (Marekani), iliyotolewa 17 Aprili 2023.
Uzito wake (weights) uko wazi: mtu yeyote anaweza kuipakua, kuiendesha na kuitumia hata kibiashara.
Ina vigezo (parameters) bilioni 13.
Ilipotoka, ilivunja rekodi katika kazi yake.
Naweza kuiendesha mwenyewe?
Ndiyo, kwenye kompyuta mpakato au kifaa chenye uwezo mkubwa zaidi.
SimuRAM ya GB 6–8
Kompyuta mpakatoRAM ya GB 16
Kompyuta yenye uwezo mkubwaGB 24 hadi 64 (kadi ya michoro au Mac yenye uwezo mkubwa)
Sevazaidi ya GB 64
Inahitaji takriban GB 8.8 za kumbukumbu (RAM) ikibanwa hadi biti 4.
Programu kama Ollama au LM Studio zinapakua na kuendesha modeli kwenye kompyuta yako, bila intaneti.
Modeli nyingine za Columbia University
Evo 2 40BArc Institute, Columbia University, Goodfire, Liquid, Nvidia, Stanford University, University of California San Francisco na University of California (UC) BerkeleyFeb 2025Biolojia
Wazi40.3B
Evo 2 7BArc Institute, Columbia University, Goodfire, Liquid, Nvidia, Stanford University, University of California San Francisco na University of California (UC) BerkeleyFeb 2025Biolojia
Grounding Dino LChinese University of Hong Kong (CUHK), Hong Kong University of Science and Technology (HKUST), International Digital Economy Academy, Microsoft Research, South China University of Technology na Tsinghua UniversityJul 2024Utambuzi wa picha
Wazi341MSimu
C
Genie 2 (bio)Columbia University na Rutgers UniversityMei 2024Biolojia