MAmmoTH-VL2 / README.md
nielsr's picture
nielsr HF staff
Correct pipeline tag
bedddae verified
|
raw
history blame
742 Bytes
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

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}
}