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 • 451 • 14 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 12.4k • 149 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 2.8k • 27 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 298 • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 9.56k • 12 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 23.2k • 15 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 10.8k • 10 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 154k • 42 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 6.74k • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 3.46k • 13 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 7.63k • 7 -
lmms-lab/llava-onevision-projectors
Updated • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 249 -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 15k