Minivla Libero90 Prismatic

🚀 MiniVLA 1B (Prismatic-Compatible Version)

This checkpoint is in a Prismatic-compatible format, useful for fully fine - tuning MiniVLA. It's built on the foundation of the Prismatic VLMs project, and offers flexibility for different fine - tuning strategies.

🚀 Quick Start

This Prismatic-compatible checkpoint is in a format that is compatible with the training script from the original Prismatic VLMs project codebase. The OpenVLA team built on top of this codebase to develop the OpenVLA model.

If you wish to fully fine - tune MiniVLA (all 1 billion parameters) via native PyTorch Fully Sharded Data Parallel (FSDP) using the Prismatic VLMs training script, this checkpoint may be useful. However, if you want to do Parameter - Efficient Fine - Tuning via LoRA, you can use the MiniVLA checkpoint linked above, which is compatible with the Hugging Face transformers library. We recommend fine - tuning via LoRA if you do not have sufficient compute to fully fine - tune a 1B - parameter model (e.g., multiple A100/H100 GPUs).

💻 Usage Examples

Basic Usage

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.

📚 Documentation

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}
}