LLaVA-OneVision: Easy Visual Task Transfer
Paper
•
2408.03326
•
Published
•
59
LLaVA-OneVision
a model good at arbitrary types of visual input
-
-
lmms-lab/LLaVA-OneVision-Mid-Data
Viewer • Updated • 563k • 397 • 14 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 8.42k • 150 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 2.59k • 28 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 292 • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 7.92k • 12 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 18.8k • 15 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 9.32k • 10 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 270k • 42 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 1.91k • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 3.08k • 13 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 1.2k • 7 -
lmms-lab/llava-onevision-projectors
Updated • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 244 -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 16.2k