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 • 354 • 16 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 9.44k • 160 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 2.36k • 28 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 277 • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 9.28k • 13 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 57.9k • 15 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 13.9k • 12 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 224k • 44 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 440 • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 2.84k • 14 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 584 • 8 -
lmms-lab/llava-onevision-projectors
Updated • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 133 -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 3.21k