pi05_piper_folding_iwr (step 4999 / final)

IWR-style corrective fine-tune of towel folding. Warm-started from pi05_piper_folding_v2 (20k), then a short low-LR pass (5000 steps @ 2e-5) on axiboai/piper_folding_iwr_v1 (277 base + 34 human-intervention episodes x2, pause-trimmed). Fixes folding failure modes. 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_iwr"))
policy = policy_config.create_trained_policy(_config.get_config("pi05_piper_folding_iwr"), ckpt)