🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
vision
7b
13b
34b
1.9M Pulls Updated 9 months ago
c43332387573 · 67B
[INST] {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }} [/INST]