wwqcleverghost/v2-handover2
xlerobot_client • Updated • 50 episodes • 166
How to use wwqcleverghost/v2-smolvla 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=wwqcleverghost/v2-smolvla \ --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=wwqcleverghost/v2-smolvlaCheckpoint 030000; 30000 training steps. Weights, configuration and normalization processors are included.
Hardware evaluation: 7/10 successful episodes.
Test records: https://huggingface.co/datasets/wwqcleverghost/handover4_test_records_20261006
The original checkpoint configurations are preserved. Load with the matching LeRobot policy and its pre/postprocessors.