Instructions to use quiet-storm/polar-bridge-vla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quiet-storm/polar-bridge-vla with Transformers:
# Load model directly from transformers import OpenVLAForActionPrediction model = OpenVLAForActionPrediction.from_pretrained("quiet-storm/polar-bridge-vla", dtype="auto") - Notebooks
- Google Colab
- Kaggle
PoLAR Bridge VLA
BridgeData V2 latent VLA checkpoint for PoLAR.
- model family:
hyperbolic_factorized_radprog - latent action token length:
5 - codebook size:
32 - predicted action horizon:
10
This repository keeps the Hugging Face model snapshot filenames intact so it can be loaded by the PoLAR evaluation code.
- Downloads last month
- 41