Fine tune of Pi0.5 using https://huggingface.co/datasets/ViVi-AI/pick_place_20260709_130127

Training command:

lerobot-train \
  --dataset.repo_id=ViVi-AI/pick_place_20260709_130127 \
  --output_dir=./outputs/train/pi05_so101_pick_place \
  --policy.repo_id=ViVi-AI/pi05_so101_pick_place \
  --policy.type=pi05 \
  --policy.pretrained_path=lerobot/pi05_base \
  --policy.device=cuda \
  --policy.dtype=bfloat16 \
  --policy.gradient_checkpointing=true \
  --policy.compile_model=true \
  --policy.train_expert_only=true \
  --policy.freeze_vision_encoder=true \
  --batch_size=32 \
  --steps=5000 \
  --job_name=pi05_so101 \
  --wandb.enable=false

Ran on an RTX 4090 and used 22 GiB of VRAM. Took 2:46 to train.

Model Card for pi05

π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository.

This policy has been trained and pushed to the Hub using LeRobot.

Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation.

Model Details

• License: apache-2.0
• Fine-tuned from: lerobot/pi05_base
• Robot type: so_follower
• Cameras: hand, workspace

Inputs & Outputs

The policy consumes these observation features and produces these action features.

Inputs

Outputs

Training Dataset

• Repository: ViVi-AI/pick_place_20260709_130127
• Episodes: 100
• Frames: 44998
• Frame rate: 30 FPS
• Task(s): "pick up the purple block and place it in the white square"

Training Configuration

How to Get Started with the Model

New to LeRobot? These guides cover the full workflow:

• Install LeRobot — set up the lerobot package.
• Hardware setup — assemble, wire, and calibrate your robot and cameras.
• Record data & train a policy — the end-to-end imitation-learning walkthrough.
• CLI cheat-sheet — quick reference for the lerobot-* commands.

The short version to run and train this policy:

Run the policy on your robot

lerobot-rollout \
  --strategy.type=base \
  --robot.type=so_follower \
  --robot.port=<your_robot_port> \
  --robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
  --policy.path=ViVi-AI/pi05_so101_pick_place \
  --task="pick up the purple block and place it in the white square" \
  --duration=60

Replace the remaining <...> placeholders with your own values: --robot.port and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.

When --strategy.type=base is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at rollout documentation.

Train your own policy

This policy type is usually fine-tuned from the pretrained base model lerobot/pi05_base:

lerobot-train \
  --dataset.repo_id=${HF_USER}/<dataset> \
  --policy.path=lerobot/pi05_base \
  --output_dir=outputs/train/<policy_repo_id> \
  --job_name=lerobot_training \
  --policy.device=cuda \
  --policy.repo_id=${HF_USER}/<policy_repo_id> \
  --wandb.enable=true

Writes checkpoints to outputs/train/<policy_repo_id>/checkpoints/.

Evaluation

No evaluation results have been provided for this policy yet.

Citation

If you use this policy, please cite the method linked in the description above, along with LeRobot:

@misc{cadene2024lerobot,
    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
    howpublished = "\url{https://github.com/huggingface/lerobot}",
    year = {2024}
}