Improved Baselines with Visual Instruction Tuning
Paper • 2310.03744 • Published • 39
LLaVa-NeXT
LLaVa-NeXT (also known as LLaVa-1.6) improves upon the 1.5 series by incorporating higher image resolutions and more reasoning/OCR datasets.
-
-
llava-hf/llava-v1.6-mistral-7b-hf
Image-Text-to-Text • 8B • Updated • 535k • 310 -
llava-hf/llava-v1.6-vicuna-7b-hf
Image-Text-to-Text • 7B • Updated • 39k • 31 -
llava-hf/llava-v1.6-vicuna-13b-hf
Image-Text-to-Text • 13B • Updated • 11.6k • 23 -
llava-hf/llava-v1.6-34b-hf
Image-Text-to-Text • 35B • Updated • 3.96k • 94 -
llava-hf/llama3-llava-next-8b-hf
Image-Text-to-Text • 8B • Updated • 20k • 52 -
llava-hf/llava-next-72b-hf
Image-Text-to-Text • 73B • Updated • 387 • 7 -
llava-hf/llava-next-110b-hf
Image-Text-to-Text • 112B • Updated • 58 • 8