Alkatt/smolvla_base_migrated

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. See the full documentation at LeRobot Docs.

---

Note: this model was migrated to support the new LeRobot preprocessing pipeline to ensure the pretrained SmolVLA model could be used for fine-tuning.

The specific command used to migrate the model was sourced from y1y2y3 at https://huggingface.co/lerobot/smolvla_base/discussions/12:

cd lerobot
python src/lerobot/processor/migrate_policy_normalization.py \
  --pretrained_path lerobot/smolvla_base \
  --output-dir ./test_smolvla_migration

The command used to upload the model to HuggingFace was:

huggingface-cli upload --repo-type model Alkatt/smolvla_base_migrated ./test_smolvla_migration

---

How to Get Started with the Model

For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval:

Train from scratch

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

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

Evaluate the policy/run inference

lerobot-record \
  --robot.type=so100_follower \
  --dataset.repo_id=<hf_user>/eval_<dataset> \
  --policy.path=<hf_user>/<desired_policy_repo_id> \
  --episodes=10

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

---

Model Details

• License: apache-2.0