LLaVA-OneVision: Easy Visual Task Transfer
Paper
•
2408.03326
•
Published
•
60
LLaVA-OneVision
a model good at arbitrary types of visual input
-
-
lmms-lab/LLaVA-OneVision-Mid-Data
Viewer • Updated • 563k • 666 • 19 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 26.3k • 167 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 1.94k • 29 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 24 • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 8.63k • 13 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 41.8k • 17 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 7.94k • 12 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 95.2k • 45 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 593 • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 3.32k • 14 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 1.35k • 8 -
lmms-lab/llava-onevision-projectors
Updated • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 246 -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 115