armnet/busybox_multitask
SO-101 • Updated • 132 episodes • 283
How to use armnet/smolvla_busybox_multitask with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=armnet/smolvla_busybox_multitask \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function
python -m lerobot.record \
--robot.type=so101_follower \
--robot.port=/dev/ttyACM0 \ # <- Use your port
--robot.id=my_blue_follower_arm \ # <- Use your robot id
--robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras
--dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording
--dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub
--dataset.episode_time_s=50 \
--dataset.num_episodes=10 \
--policy.path=armnet/smolvla_busybox_multitaskFull-component fine-tune of SmolVLA on SO-101 BusyBox multitask.
| Policy | SmolVLA (lerobot/smolvla_base, vision + VLM + expert) |
| Dataset | armnet/busybox_multitask (132 episodes, 27 tasks) |
| Cameras | top → camera1, wrist → camera2, front → camera3 |
| Training | 1× H100 NVL, batch 32, 20k steps, horizon 50 |
| Result | loss 0.468 → 0.025. 7 h 23 m. Finished 2026-10-25 18:43 UTC |
| W&B | zt42xxfc |
checkpoint-20000/ is the final step.
checkpoint-5000/ · checkpoint-10000/ · checkpoint-15000/ · checkpoint-20000/
from huggingface_hub import snapshot_download
ckpt = snapshot_download("armnet/smolvla_busybox_multitask", allow_patterns="checkpoint-20000/**")