OpenVLA 7B
openvla
OpenVLA 7B (openvla-7b) is an open vision-language-action model trained on 970K robot manipulation episodes from the Open X-Embodiment dataset.
Source notes
OpenVLA 7B (openvla-7b) is an open vision-language-action model trained on 970K robot manipulation episodes from the Open X-Embodiment dataset. The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via (parameter-efficient) fine-tuning.
- Code
- Unverified
- Weights
- Available
- Checkpoint
- Available
- License
- mit
Decision summary
VLA training
Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
Run a checkpoint loading smoke test before marking the model pipeline-tested.
Release history
Source-backed release timing for this canonical model record.
- Official source
Checkpoint published
Release timing is recorded from the official source creation date.
Selection readiness
Evidence dimensions for deciding whether this model is ready to inspect, compare, or adopt. Scores describe catalog evidence, not task performance.
Published evaluation
How scores work76/100
Useful
5/6 dimensions scored · 63% confidence
Engineering checks (OBRS) behind this record
Needs Audit
OBRS metadata and reported test evidence. A breakdown behind Selection readiness, not a separate score or an independent OpenBot certification.
- A passing real-hardware test report is required.
- A passing ingestion/pipeline test report is required.
- A passing privacy and provenance review is required.
Why these scores
The strongest decision reasons behind Selection readiness.
Artifact availability
UsefulCheckpoint files were verified in the official repository metadata.
Training and loading reproducibility
UsefulConfiguration files are present; runtime loading is not tested.
Evaluation evidence
UnknownNo structured evaluation evidence has been verified.
Data requirements
Declared loop-data needs, missing evidence, and the next checks that matter.
Observation / ego video
video · image-text-to-text
Language intent / task phase
language
Action / robot state
actions · feature-extraction
Sim-real / embodiment metadata
Descriptive model record
Critical gaps
Core categories are represented. Interface alignment and data quality still require verification.
Linked datasets
Signal-level links only. Verify runtime interfaces before use.
No related catalog datasets are linked to this model yet.
More evidenceShowHide
Additional decision dimensions
Access and license are declared by the source.
75 · c85Required signal categories are structured; exact tensor and action interfaces still need verification.
76 · c70Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
70 · c55Artifact facts
- availability
- metadata_verified
- open
- repository metadata
- license
- metadata_verified
- mit
- Hugging Face model card license metadata
- repository.files
- metadata_verified
- .gitattributes · README.md · added_tokens.json · config.json · configuration_prismatic.py · generation_config.json · model-00001-of-00003.safetensors · model-00002-of-00003.safetensors · model-00003-of-00003.safetensors · model.safetensors.index.json · modeling_prismatic.py · preprocessor_config.json · processing_prismatic.py · processor_config.json · special_tokens_map.json · tokenizer.json · tokenizer.model · tokenizer_config.json
- repository file tree
- dataset.signals
- official_claim
- video · actions · language · feature-extraction · image-text-to-text
- README/card declaration
- dataset.scale
- metadata_verified
- label: repository size · value: 15.09GB
- repository blob sizes
- model.weight_files
- metadata_verified
- repository: openvla/openvla-7b · count: 3 · sample files: model-00001-of-00003.safetensors · model-00002-of-00003.safetensors · model-00003-of-00003.safetensors
- Hugging Face model metadata siblings
- model.checkpoint_files
- metadata_verified
- repository: openvla/openvla-7b · count: 3 · sample files: model-00001-of-00003.safetensors · model-00002-of-00003.safetensors · model-00003-of-00003.safetensors
- Hugging Face model metadata checkpoint files
- model.config_files
- metadata_verified
- repository: openvla/openvla-7b · count: 5 · sample files: config.json · generation_config.json · preprocessor_config.json · processor_config.json · tokenizer_config.json
- Hugging Face model metadata siblings
- model.required_signals
- official_claim
- video · actions · language · feature-extraction · image-text-to-text
- Official model documentation and curated signal mapping
- model.training_data
- official_claim
- dataset: Open X-Embodiment · robot manipulation episodes: 970000
- OpenVLA-7B model card, model summary
- license.weights
- metadata_verified
- mit
- Hugging Face model card license metadata
- release_timing
- metadata_verified
- 2024-06-10T16:35:59.000Z
- Existing published Catalog release-date evidence