Quick Links
Tomato Grasping GR00T Model
Fine-tuned NVIDIA GR00T model for tomato grasping task.
Model Details
- Base Model: nvidia/GR00T-N1.5-3B
- Task: Tomato grasping and placement
- Training Steps: 50,000
- Final Loss: 0.037
- Training Time: 4 hours 3 minutes
Hardware
- Robot: SO101 Follower
- Cameras: Wrist + Side view (Intel RealSense)
- DOF: 6 (5 joints + gripper)
Dataset
- Episodes: 40
- Total Frames: 12,069
- Task: "Grasp the tomato and place it in the container"
- Downloads last month
- 8
# Load model directly from transformers import GR00T_N1_5 model = GR00T_N1_5.from_pretrained("c299m/tomato-grasping-gr00t", device_map="auto")