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 • 624 • 12 -
lmms-lab/LLaVA-OneVision-Data
Viewer • Updated • 3.72M • 20.1k • 134 -
lmms-lab/LLaVA-NeXT-Data
Viewer • Updated • 779k • 3.1k • 22 -
lmms-lab/llavanext-qwen-siglip-tokenizer
Text Generation • Updated • 115k • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-si
Text Generation • Updated • 92k • 9 -
lmms-lab/llava-onevision-qwen2-0.5b-ov
Text Generation • Updated • 60k • 12 -
lmms-lab/llava-onevision-qwen2-7b-si
Text Generation • Updated • 25.4k • 8 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • Updated • 116k • 35 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • Updated • 22.5k • 1 -
lmms-lab/llava-onevision-qwen2-72b-ov-sft
Text Generation • Updated • 5.56k • 11 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • Updated • 95.4k • 5 -
lmms-lab/llava-onevision-projectors
Updated • 3 -
lmms-lab/llava-onevision-qwen2-0.5b-mid-stage-a4
Updated • 2.8k -
lmms-lab/llava-onevision-qwen2-7b-mid-stage-a4
Updated • 4.7k