Downloads · 30 days
22
24% of all-time downloads
MINT-SJTU/starvla_metaworld_qwenpiv3_la_finetune
starvla_metaworld_qwenpiv3_la_finetune is a robotics model from MINT-SJTU. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains the evaluated StarVLA/QwenPI-v3 checkpoint for MetaWorld MT50.
Downloads · 30 days
22
24% of all-time downloads
All-time downloads
93
Public
Repo size
9.4 GB
Likes
0
Public
Click a slice to open those files.
.pt9.4 GB · 100%
From the Hugging Face model README
This repository contains the evaluated StarVLA/QwenPI-v3 checkpoint for MetaWorld MT50.
starvla_metaworld_qwenpiv3_la_finetune6000070.9%Qwen/Qwen2.5-VL-3B-Instructcheckpoints/steps_60000_pytorch_model.pt
config.yaml
config.full.yaml
dataset_statistics.json
dataset_statistics.json is required for action denormalization. Keep the directory structure unchanged if your inference server expects the checkpoint directory layout used by the released config.
This checkpoint is intended to be loaded with the StarVLA/QwenPI-v3 codebase. The public configs use Qwen/Qwen2.5-VL-3B-Instruct as the base VLM path.
For inference, load:
checkpoints/steps_60000_pytorch_model.pt
For continued training or evaluation on your own machine, update:
datasets:
vla_data:
data_root_dir: ./metaworld_starvla
to your local MetaWorld data path.
If you use this checkpoint, please cite the corresponding StarVLA and LA4VLA work and this model repository.
LA4VLA:
@misc{lin2026la4vlalearningactseeing,
title={LA4VLA: Learning to Act without Seeing via Language-Action Pretraining},
author={Tao Lin and Yuxin Du and Yiran Mao and Zewei Ye and Yilei Zhong and Bing Cheng and Yiming Wang and Jiting Liu and Yang Tian and Junchi Yan and Feiran Wu and Zenan Meng and Hu Wei and Yuqian Fu and Gen Li and Bo Zhao},
year={2026},
eprint={2606.27295},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2606.27295},
}
StarVLA:
@article{community2026starvla,
title={StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing},
author={Community, StarVLA},
journal={arXiv preprint arXiv:2604.05014},
year={2026},
eprint={2604.05014},
archivePrefix={arXiv},
primaryClass={cs.RO}
}