LLaVA-OneVision: Easy Visual Task Transfer
Paper
•
2408.03326
•
Published
•
58
LLaVA-OneVision
a model good at arbitrary types of visual input
-
-
lmms-lab/LLaVA-OneVision-Mid-Data
Viewer • Updated • 563k • 54 • 7 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 29.3k • 105 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 806 • 17 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 102k • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 13k • 8 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 103k • 4 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 8.39k • 7 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 47k • 23 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 9.25k • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 20.2k • 9 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 3.44k • 1 -
lmms-lab/llava-onevision-projectors
Updated • 1 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 678 -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 1.01k