pi05_piper_folding_v2 (step 19999 / final)

pi0.5 (action_horizon 50) full fine-tune of pi05_base on axiboai/piper_laundry_calibrated_v2 (277 episodes towel folding). Converged baseline (loss ~0.0045). Inference artifacts only. Prompt: pick towel from pile, fold and stack

import pathlib
from huggingface_hub import snapshot_download
from openpi.training import config as _config
from openpi.policies import policy_config
ckpt = pathlib.Path(snapshot_download("axiboai/pi05_piper_folding_v2"))
policy = policy_config.create_trained_policy(_config.get_config("pi05_piper_folding_v2"), ckpt)