YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
A2 Pretrained Model
Pretrained ViLGP3D model for 6-DOF grasp pose selection in tabletop manipulation.
Model Architecture
- Network: CLIPAction (CLIP-based action selection with cross-attention)
- Width: 768
- Layers: 1
- Heads: 8
- Action Dim: 7 (xyz + quaternion)
- Features: RoPE (Rotary Position Encoding)
Usage
from lerobot_policy_a2 import A2Policy, A2Config
# Load pretrained model
policy = A2Policy.from_pretrained("dgrachev/a2_pretrained")
Training Data
Trained on simulated tabletop grasping with UR5e robot and Robotiq gripper.
Related
- Environment: Install with
pip install lerobot[a2] - Assets: dgrachev/a2_assets
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support