Robotics (VLA) · Stanford / OpenVLA
OpenVLA 7B
7B Llama 2-based VLA trained on Open X-Embodiment.
Datasheet
Maker | Stanford / OpenVLA |
|---|---|
Parameters | 7.54 BVerifiedsafetensors.total from the HF API Source |
Licence | MITVerified |
Access | Public download |
Task (HF pipeline) | robotics |
First published on HF | 2024-06-10 |
Last updated on HF | 2026-02-17 |
Weights in memory | 15 GB at 16-bit · 4.6 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
76.5%
LIBERO, average success rate (4 suites) · #3 of 3 scored in this category
OpenVLA (7B) row. Source
Used in
The description summarises the model card at https://huggingface.co/openvla/openvla-7b. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.