Model Card for YoungTO/pi05-grab-the-brush-v1-step3000

This repository contains a pi05 policy exported from SparkMind.

Summary

• Source run: checkpoints
• Exported checkpoint: 010000
• Policy type: pi05
• Dataset id: YoungTO/grab-the-brush-v1

Features

• Input features: observation.images.cam_head, observation.images.cam_wrist, observation.state
• Output features: action

Files

• model.safetensors: policy weights
• config.json: policy config
• train_config.json: training config snapshot
• policy_preprocessor*.json|safetensors: input processing pipeline
• policy_postprocessor*.json|safetensors: output processing pipeline
• robot_io.json: optional dataset robot/state/action/camera I/O contract

Inference

python examples/learning_il/01a_demo_ACT.py \
  --task PushT \
  --hf_repo YoungTO/pi05-grab-the-brush-v1-step3000 \
  --inference

Adjust --task to match the environment you evaluate against.

Notes

Local-only paths in train_config.json were sanitized during export unless --keep-local-paths was used.