SPHINX (Llama 2 13B) ni modeli ya kutambua picha, lugha na uchakataji wa data mseto iliyoundwa na Chinese University of Hong Kong (CUHK), Shanghai AI Lab na ShanghaiTech University (China, Hong Kong), iliyotolewa 13 Novemba 2023.
Uzito wake uko wazi na unaweza kuipakua, lakini leseni yake ina masharti (kwa mfano kwa makampuni makubwa sana).
Ina vigezo (parameters) bilioni 19.9.
Ilipotoka, ilivunja rekodi katika kazi yake.
Naweza kuiendesha mwenyewe?
Ndiyo, kwenye kompyuta yenye uwezo mkubwa 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 12.9 za kumbukumbu (RAM) ikibanwa hadi biti 4.
Inahitaji kadi ya michoro (GPU) yenye kumbukumbu kubwa au kompyuta ya Mac yenye kumbukumbu ya GB 32–64.
Modeli nyingine za Chinese University of Hong Kong (CUHK)
MinerU2.5Peking University, Shanghai AI Lab na Shanghai Jiao Tong UniversitySep 2025Lugha, Utambuzi wa picha
Wazi1.2BSimu
C
Lumina-Image-2.0Chinese University of Hong Kong (CUHK), Krea AI, Shanghai AI Lab, Shanghai Jiao Tong University na University of SydneyMar 2025Kutengeneza picha
Wazi2.6BSimu
C
OREAL 32BChinese University of Hong Kong (CUHK), InnoHK, Shanghai AI Lab na Shanghai Jiao Tong UniversityFeb 2025Hisabati, Lugha
Wazi32BKompyuta yenye uwezo mkubwa
C
OREAL 7BChinese University of Hong Kong (CUHK), InnoHK, Shanghai AI Lab na Shanghai Jiao Tong UniversityFeb 2025Hisabati, Lugha
Wazi7BKompyuta mpakato
C
Eurus-2-7B-PRIMECUHK Shenzhen Research Institute, Peking University, Shanghai AI Lab, Shanghai Jiao Tong University, Tsinghua University na University of Illinois Urbana-Champaign (UIUC)Jan 2025Hisabati, Lugha