|
|
--- |
|
|
base_model: lerobot/smolvla_base |
|
|
datasets: fracapuano/test_async_e2e |
|
|
library_name: lerobot |
|
|
license: apache-2.0 |
|
|
model_name: smolvla |
|
|
pipeline_tag: robotics |
|
|
tags: |
|
|
- robotics |
|
|
- smolvla |
|
|
- lerobot |
|
|
--- |
|
|
|
|
|
# Model Card for smolvla |
|
|
|
|
|
This `smolvla` policy is a ready-to-use example from the tutorial paper [Robot Learning: A Tutorial](https://huggingface.co/papers/2510.12403). |
|
|
|
|
|
**Project Page:** https://huggingface.co/spaces/lerobot/robot-learning-tutorial |
|
|
**Code:** https://github.com/fracapuano/robot-learning-tutorial |
|
|
|
|
|
[SmolVLA](https://huggingface.co/papers/2506.01844) 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](https://github.com/huggingface/lerobot). |
|
|
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index). |
|
|
|
|
|
--- |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy). |
|
|
Below is the short version on how to train and run inference/eval: |
|
|
|
|
|
### Train from scratch |
|
|
|
|
|
```bash |
|
|
python -m lerobot.scripts.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 |
|
|
|
|
|
```bash |
|
|
python -m 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 |
|
|
|
|
|
* **Model License:** apache-2.0 |
|
|
* **Related Tutorial Paper:** [Robot Learning: A Tutorial](https://huggingface.co/papers/2510.12403) |
|
|
* **Tutorial Project Page:** https://huggingface.co/spaces/lerobot/robot-learning-tutorial |
|
|
* **Tutorial Code:** https://github.com/fracapuano/robot-learning-tutorial |
|
|
* **Tutorial Content License:** The written content of the tutorial is licensed under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](http://creativecommons.org/licenses/by-nc-sa/4.0/). |
|
|
* **Tutorial Code Examples License:** Source code examples in the tutorial's `snippets/` directory are licensed under the [MIT License](https://opensource.org/licenses/MIT). |
