Minivla Wrist Vq Libero90 Prismatic

🚀 MiniVLA 1B Wrist VQ (Prismatic-Compatible Version)

This checkpoint is compatible with the training script from the original Prismatic VLMs project. It allows for full fine - tuning of MiniVLA using native PyTorch FSDP.

🚀 Quick Start

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

If you want 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 prefer 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 don't have sufficient compute 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}
}