LLaVA-Mini
LLaVA-Mini:Efficient Image and Video Large Multimodal Models
In primo piano
5 Voti
Descrizione
LLaVA-Mini👏is an efficient LMM for image/video understanding using 1 vision token, offering: (1)⏩fast response (40ms per image) (2)🖥️less VRAM usage (support 3-hour video understanding on 24GB GPU).