Robotics
Transformers
English
multimodal
vision-language-action
univla
action-decoder
continuous-control
Instructions to use VLA-Arena/univla-action-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VLA-Arena/univla-action-decoder with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("VLA-Arena/univla-action-decoder", dtype="auto") - Notebooks
- Google Colab
- Kaggle