Model Card for vla0-smol

Read about the model here: https://robot-learning-collective.github.io/vla-0-smol This is VLA-0-Smol trained on the Libero dataset.

Model type not recognized — please update this template.

This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.

---

How to Get Started with the Model

For a complete walkthrough, see the training guide.

Support of the model is implemented in repo: https://github.com/Robot-Learning-Collective/lerobot-experiments

Below is the short version on how to train and run inference/eval:

Train from scratch on PushT

lerobot-train --config_path=configs/vla0_smol.json

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

Evaluate the policy on Libero

lerobot-eval \
  --policy.path="Robot-Learning-Collective/VLA-0-Smol" \
  --policy.n_action_steps=0 \
  --policy.ensemble_size=8 \
  --env.type=libero \
  --env.task=libero_object \
  --eval.batch_size=2

Prefix the dataset repo with eval_ and supply --policy.path pointing to a local or hub checkpoint.

---

Model Details

• License: apache-2.0