Robotics
Transformers
Safetensors
English
openvla
feature-extraction
vla
image-text-to-text
multimodal
pretraining
custom_code
Instructions to use openvla/openvla-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openvla/openvla-7b with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("openvla/openvla-7b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signature47a0ec7
-
Update modeling_prismatic.py to match public GitHub repo
Check input_ids before adding the special empty token ('') rather than adding it unconditionally.31f090d
-
Update README.md
Verified signaturee5822cc
-
Update README.md
Verified signaturef7ad868 -
Update README.md
Verified signature0d9b63f -
Update README.md
Verified signaturecb2124a -
Update README.md
Verified signature423cc6c -
Update README.md
Verified signature742ce85
-
Upload processor
Verified signatured6e88ec -
Upload processor
Verified signaturedc8f331 -
Upload OpenVLAForActionPrediction
Verified signaturecf0c8cb -
Upload config
Verified signature43a4a81 -
initial commit
Verified signature8f441e0