pi05_tube_full

Full fine-tuned UR5 OpenPI/Pi0.5 policy checkpoint for the pi05_tube_full deployment preset.

This upload contains all available inference checkpoint steps from the local run: 10000, 20000, 30000. The optimizer state is intentionally not uploaded by default because it is not needed for inference and is much larger than the model weights. Set UPLOAD_OPTIMIZER=1 when running the uploader if optimizer states are really needed.

Files

• checkpoints/<step>/model.safetensors: PyTorch model weights for each uploaded step.
• checkpoints/<step>/metadata.pt: original checkpoint metadata from training.
• checkpoints/<step>/metadata.json: JSON-readable metadata summary for each step.
• checkpoints/<step>/assets/norm_stats.json: normalization stats used for inference.
• assets/norm_stats.json: normalization stats used for inference.
• configs/deployment.env: deployment preset used in vla_ur5.
• configs/*.py and configs/*.sh: source/config snapshots needed to reproduce training/inference wiring.

Training And Inference Config

• OpenPI config: pi05_tube_force_depth_joint_full_5090
• Family: Pi0.5 baseline
• Uploaded checkpoint steps: 10000, 20000, 30000
• Default deployment step: 30000
• Action horizon: 50
• Denoising steps used in deployment: 10
• Dataset/norm stats source: giakhuyendihoc/ur5_tube_full_tcp240_converted
• Training time hours: 4.985389479994774

Prompt:

place the lab test tube with red contents and place it in the smaller lab test tube holder

Loading

Use the local vla_ur5 / OpenPI deployment code:

TASK=pi05_tube_full bash deployment/scripts/serve_policy.sh

When loading directly from this HF repo, use checkpoints/30000 as the checkpoint directory for the default final model.

The matching config name is:

pi05_tube_force_depth_joint_full_5090

Notes

The config snapshots are included so other users can reconstruct the architecture and transforms even if the local repository evolves.