Downloads · 30 days
23
9% of all-time downloads
koboshchan/Lumine-Agent-Pretraining-VL-7B
Lumine-Agent-Pretraining-VL-7B is a image-text-to-text model from koboshchan. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
Trained on 30 minutes of game play. Based on Qwen2-VL-7B
Downloads · 30 days
23
9% of all-time downloads
All-time downloads
265
Public
Parameters
8.3B
33.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.6 GB · 100%
From the Hugging Face model README
Trained on 30 minutes of game play. Based on Qwen2-VL-7B
https://github.com/zlc1004/Lumine
@misc{tan2025lumineopenrecipebuilding,
title={Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds},
author={Weihao Tan and Xiangyang Li and Yunhao Fang and Heyuan Yao and Shi Yan and Hao Luo and Tenglong Ao and Huihui Li and Hongbin Ren and Bairen Yi and Yujia Qin and Bo An and Libin Liu and Guang Shi},
year={2025},
eprint={2511.08892},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2511.08892},
}