---
license: mit
language:
- en
base_model:
- Qwen/Qwen2-VL-7B
new_version: limuyu011/JarvisVLA-Qwen2-VL-7B
pipeline_tag: image-text-to-text
library_name: transformers
datasets:
- CraftJarvis/minecraft-vla-sft
tags:
- VLA
- Minecraft
---
## Introduction
**JarvisVLA-Qwen2-VL-7B** is a Visual-Language-Action (VLA) model specifically tailored for the open-world game **Minecraft**. Based on human language instructions, **JarvisVLA-Qwen2-VL-7B** masters thousands of in-game skills, empowering endless creativity and interaction in Minecraft’s expansive universe!
- Paper: [https://craftjarvis.github.io/JarvisVLA/files/jarvis_vla_draft.pdf](https://craftjarvis.github.io/JarvisVLA/files/jarvis_vla_draft.pdf)
- Github: [https://github.com/CraftJarvis/JarvisVLA](https://github.com/CraftJarvis/JarvisVLA)
- Project: [https://craftjarvis.github.io/JarvisVLA/](https://craftjarvis.github.io/JarvisVLA/)
## Citation
```

@article{li2025jarvisvla,
  title   = {JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse},
  author  = {Muyao Li and Zihao Wang and Kaichen He and Xiaojian Ma and Yitao Liang},
  year    = {2025}
}

```