peter1111aaaa/my_smolVLA_new_v1

Model Card for smolvla

SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.

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

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

---

Model Details

• License: apache-2.0
• Fine-tuned from: lerobot/smolvla_base
• Robot type: omx_follower
• Cameras: front, wrist

Inputs & Outputs

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

Inputs

Feature	Type	Shape
observation.state	STATE	(6,)
observation.images.camera1	VISUAL	(3, 256, 256)
observation.images.camera2	VISUAL	(3, 256, 256)
observation.images.camera3	VISUAL	(3, 256, 256)

Outputs

Feature	Type	Shape
action	ACTION	(6,)

Training Dataset

• Repository: peter1111aaaa/omx-smolvla-dataset-merged_20260817_172234
• Episodes: 451
• Frames: 167728
• Frame rate: 30 FPS
• Task(s): "Pick up one yellow banana and put it in the basket.", "Clean up the table.", "Place the biscuit in the grocery basket.", "Put the cake slice into the basket.", "Place the ice cream bar in the shopping basket.", "Grasp the sandwich.", "Grasp the milk box.", "Grasp the swirl cake.", "Grasp the cake.", "Put all the items into the basket.", "Drop the roll cake in the basket.", "Drop the ice cream bar in the basket.", "Pick up the sandwich.", "Grasp the cookie.", "Grab the roll cake.", "Put the biscuit into the basket.", "Place the roll cake in the grocery basket.", "Grab the pink ice cream bar.", "Grab the chocolate milk.", "Grab the slice of cake.", "Place the sandwich in the grocery basket.", "Put the ice cream bar into the basket.", "Drop the chocolate milk into the grocery basket.", "Pick up the chocolate milk box.", "Put the sandwich into the basket.", "Grab the biscuit.", "Pick up the ice cream bar.", "Put the chocolate milk box into the basket.", "Pick up the cake slice.", "Pick up the roll cake.", "Drop the cake slice into the basket.", "Pick up the biscuit.", "Drop the sandwich in the basket.", "Clear the workspace by moving everything to the basket.", "Place the chocolate milk box in the basket.", "Place the cake slice in the grocery basket.", "Drop the biscuit in the basket.", "Put the roll cake into the basket.", "Grab the sandwich.", "Grasp the ice cream."

Training Configuration

Setting	Value
Training steps	50000
Batch size	8
Optimizer	adamw
Learning rate	0.0001
Seed	1000
LeRobot version	0.6.2

---

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=omx_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=peter1111aaaa/my_smolVLA_new_v1 \
  --task="Pick up one yellow banana and put it in the basket." \
  --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/smolvla_base:

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