wumengyangok
/

LLaVA-SpaceSGG

Visual Question Answering

Model card Files Files and versions

LLaVA-SpaceSGG baseline models for scene graph generations. Paper: https://arxiv.org/abs/2412.06322v1

Code: https://github.com/Endlinc/LLaVA-SpaceSGG

Downloads last month: 4

Safetensors

Model size

13B params

Tensor type

F16

·

Model tree for wumengyangok/LLaVA-SpaceSGG

Base model

liuhaotian/llava-v1.5-13b

Finetuned

(4)

this model

Paper for wumengyangok/LLaVA-SpaceSGG

LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations

Paper • 2412.06322 • Published Dec 9, 2024