metadata
base_model: lerobot/smolvla_base
library_name: lerobot
license: apache-2.0
model_name: smolvla
pipeline_tag: robotics
tags:
- robotics
- smolvla
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.
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
python lerobot/scripts/train.py --dataset.repo_id=<user_or_org>/<dataset> --policy.type=act --output_dir=outputs/train/<desired_policy_repo_id> --job_name=lerobot_training --policy.device=cuda --policy.repo_id=<user_or_org>/<desired_policy_repo_id> --wandb.enable=true
Writes checkpoints to outputs/train/<desired_policy_repo_id>/checkpoints/.
Evaluate the policy
python -m lerobot.record --robot.type=so100_follower --dataset.repo_id=<user_or_org>/eval_<dataset> --policy.path=<user_or_org>/<desired_policy_repo_id> --episodes=10
Prefix the dataset repo with eval_ and supply --policy.path pointing to a local or hub checkpoint.