metadata
base_model:
- MAmmoTH-VL/MAmmoTH-VL-8B
datasets:
- TIGER-Lab/VisualWebInstruct
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
Introduction
MAmmoTH-VL2, the model trained with VisualWebInstruct.
Links
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}
}