Pi-0.5 (rm65b stack blocks)
LeRobot policy checkpoints uploaded by goal_gen/upload_hf_checkpoints.sh.
Each subfolder contains the deployment-ready pretrained_model/ payload
(model.safetensors + config.json + pre/postprocessor + train_config.json).
| Subfolder | Train step | Final train loss |
|---|---|---|
checkpoint-030000 |
30,000 | 0.018 |
Usage
from huggingface_hub import snapshot_download
ckpt_dir = snapshot_download(
"JayCao99/pi05-rm65b-stack-v0.0",
allow_patterns="checkpoint-030000/*",
)
from lerobot.policies.pi05.modeling_pi05 import PI05Policy
policy = PI05Policy.from_pretrained(f"{ckpt_dir}/checkpoint-030000")