mvp-lab/LLaVA-OneVision-1.5-Instruct-Data
Viewer
• Updated
• 21.9M • 78.5k • 65
LLaVA-OneVision-1.5
https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5
Note Stage-2: Visual Instruction Tuning.
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M
Viewer • Updated • 91.5M • 164k • 59Note Stage-1.5: High-Quality Knowledge Learning,
-
lmms-lab/LLaVA-OneVision-1.5-8B-Instruct
Image-Text-to-Text • 9B • Updated • 39k • 62 -
lmms-lab/LLaVA-OneVision-1.5-4B-Instruct
Image-Text-to-Text • 5B • Updated • 3.44k • 17 -
LLaVA OneVision 1.5
📉12Interact with a multimodal chatbot using text and images
-
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Paper • 2509.23661 • Published • 48
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-Webdataset-Quick-Start-3M
Updated • 6.13k • 2Note Stage-1.5: High-Quality Knowledge Learning, this is a subset for quick start.
mvp-lab/LLaVA-NeXT-780k-webdataset
Updated • 818Note Stage-2: Visual Instruction Tuning, this is a subset for quick start.
mvp-lab/LLaVA-558K-Webdataset
Updated • 375 • 4Note Stage-1: Language-Image Alignment