Video Instruction Tuning With Synthetic Data
Paper • 2410.02713 • Published • 41
LLaVA-Video
Models focus on video understanding (previously known as LLaVA-NeXT-Video).
-
-
lmms-lab/LLaVA-Video-178K
Viewer • Updated • 1.63M • 30.9k • 198 -
lmms-lab/LLaVA-Video-7B-Qwen2
Video-Text-to-Text • 8B • Updated • 15.9k • 127 -
lmms-lab/LLaVA-Video-72B-Qwen2
Text Generation • 73B • Updated • 88 • 21 -
lmms-lab/LLaVA-Video-7B-Qwen2-Video-Only
Text Generation • 8B • Updated • 44 • 5 -
lmms-lab/LLaVA-NeXT-Video-32B-Qwen
Video-Text-to-Text • 33B • Updated • 12 • 17 -
lmms-lab/LLaVA-NeXT-Video-7B-DPO
Video-Text-to-Text • 7B • Updated • 393 • 29 -
lmms-lab/LLaVA-NeXT-Video-7B
Video-Text-to-Text • 7B • Updated • 251 • 51