Entity dossier

Model model--openvla-7b

OpenVLA 7B

Open 7B VLA trained on the Open X-Embodiment mixture.

Also known as OpenVLA

Reviewed relationships 1

  1. Verified

    OpenVLA 7B trained on Open X-Embodiment Dataset

    Scope published training mixture

    Boundary The paper states 970k real-robot episodes from Open X-Embodiment.

    First observed · reviewed · [R2] · Show in graph

Canonical evidence claims 11

Claims are projected from authored tables. A dash remains an explicit missing value; it is never filled from a neighboring product or name match.

Robot foundation models — policy weights, not URDF assets Policy Model 11 rows · 2 declared gaps

MetricValue and evidence
Code licenseproject and training code published; see repository [M2]
Kindopen VLA on Llama 2 + SigLIP/DINOv2 [R2]
PaperarXiv:2406.09246 [R2]
Parameter count7B [R2]
Public API Declared gap
Public benchmark tablepaper tables only [R2]
Public datearXiv 2024-06-13; CoRL 2025 [R2]
Published latency / rate Declared gap
Stated embodiments in the sourceOpen X-Embodiment mixture (many arms) [R2]
Stated training data970k real-robot episodes from Open X-Embodiment [R2]
WeightsHF openvla/openvla-7b; backbone is Llama 2 (Community License) [M2] [R2]

Source ledger 2

  1. [M2]ManualOpenVLA — project page and Hugging Face openvla/openvla-7b. Type: official project / weights. Retrieved: 2026-08-29.Retrieved
  2. [R2]ResearchKim et al. — OpenVLA: An Open-Source Vision-Language-Action Model. Type: research paper. ID: arXiv:2406.09246. Venue: CoRL 2025. Retrieved: 2026-08-29.Retrieved

What is not inferred

No fuzzy entity matching, adjacent-column borrowing, universal compatibility, commercial maturity, or checkpoint-to-product identity. Absence of a relation means unreviewed or unsupported here—not proven incompatibility.