LLaVA 1.5

LLaVA 1.5 ni modeli ya lugha, kutambua picha na uchakataji wa data mseto iliyoundwa na Microsoft Research na University of Wisconsin Madison (Marekani), iliyotolewa 5 Novemba 2023.

Uzito wake uko wazi na unaweza kuipakua, lakini leseni yake ina masharti (kwa mfano kwa makampuni makubwa sana).

Ina vigezo (parameters) bilioni 13.

Ilipotoka, ilivunja rekodi katika kazi yake.

Naweza kuiendesha mwenyewe?

Ndiyo, kwenye kompyuta mpakato au kifaa chenye uwezo mkubwa zaidi.

  1. SimuRAM ya GB 6–8
  2. Kompyuta mpakatoRAM ya GB 16
  3. Kompyuta yenye uwezo mkubwaGB 24 hadi 64 (kadi ya michoro au Mac yenye uwezo mkubwa)
  4. 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 Microsoft Research

  1. Phi-4Microsoft ResearchDes 2024Lugha
    Wazi14BKompyuta mpakato
  2. 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
  3. CARPMicrosoft ResearchFeb 2024Biolojia
    Wazi643M
  4. LLaVA-NeXT-34B (LLaVA-1.6)ByteDance, Nanyang Technological University, University of California (UC) Berkeley na University of Wisconsin MadisonJan 2024Data mseto, Lugha
    Wazi34.8BKompyuta yenye uwezo mkubwa
  5. HiFi - NNBasecamp Research, Microsoft Research, Molecular Institute of Biology na Technical University of MunichDes 2023Biolojia
    Wazi3M
  6. Orca 2-13BMicrosoft ResearchNov 2023Lugha
    Wazi, si kwa biashara13BKompyuta mpakato