Introduction

MAmmoTH-VL2, the model trained with VisualWebInstruct.

Links

Github| Paper| Website

Citation

@article{visualwebinstruct,
    title={VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search},
    author = {Jia, Yiming and Li, Jiachen and Yue, Xiang and Li, Bo and Nie, Ping and Zou, Kai and Chen, Wenhu},
    journal={arXiv preprint arXiv:2503.10582},
    year={2025}
}
Downloads last month
18
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for TIGER-Lab/MAmmoTH-VL2

Base model

Qwen/Qwen2.5-7B
Finetuned
(1)
this model

Dataset used to train TIGER-Lab/MAmmoTH-VL2