Minivla Vq Libero90 Prismatic

🚀 MiniVLA VQ 1B (Prismatic-Compatible Version)

This checkpoint is in a Prismatic-compatible format, useful for fully fine - tuning MiniVLA. It's built upon the original Prismatic VLMs project, and the OpenVLA team developed the OpenVLA model on it.

🚀 Quick Start

This Prismatic-compatible checkpoint is beneficial when you want to fully fine-tune MiniVLA (all 1 billion parameters) using native PyTorch Fully Sharded Data Parallel (FSDP) with the Prismatic VLMs training script. If you prefer Parameter - Efficient Fine - Tuning via LoRA, you can use the MiniVLA checkpoint mentioned above, which is compatible with the Hugging Face transformers library. We suggest fine - tuning via LoRA if you don't have enough computing resources to fully fine - tune a 1B - parameter model (e.g., multiple A100/H100 GPUs).

📚 Documentation

See the MiniVLA GitHub README for instructions on how to use this checkpoint for full fine - tuning.

📄 License

This project is licensed under the MIT license.

📚 Citation

BibTeX:

@article{belkhale24minivla,
    title={MiniVLA: A Better VLA with a Smaller Footprint},
    author={Suneel Belkhale and Dorsa Sadigh},
    url={https://github.com/Stanford-ILIAD/openvla-mini}
    year={2024}
}