| --- |
| pipeline_tag: robotics |
| tags: |
| - lerobot |
| library_name: lerobot |
| datasets: |
| - TekbotRobotics/svla_so101_pickplace_flags_sorting |
| --- |
| ## SmolVLA: A vision-language-action model for affordable and efficient robotics |
|
|
| Resources and technical documentation: |
|
|
|
|
| [Train using Google Colab Notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/lerobot/training-smolvla.ipynb#scrollTo=ZO52lcQtxseE) |
|
|
| [SmolVLA HF Documentation](https://huggingface.co/docs/lerobot/smolvla) |
|
|
| Designed by Tekbot Robotics and Inspired from Hugging Face. |
|
|
| This model was finetuned on [hugging Face base model](https://huggingface.co/lerobot/smolvla_base/). |
|
|
| Before proceeding to the next steps, you need to properly install the environment by following [Installation Guide](https://huggingface.co/docs/lerobot/installation) on the docs. |
|
|
| Install smolvla extra dependencies: |
| ```bash |
| pip install -e ".[smolvla]" |
| ``` |
|
|
| Example of finetuning the smolvla pretrained model (`smolvla_base`): |
| ```bash |
| python lerobot/scripts/train.py \ |
| --policy.path=lerobot/smolvla_base \ |
| --dataset.repo_id=TekbotRobotics/svla_so101_pickplace_flags_sorting \ |
| --batch_size=8 \ |
| --steps=2000 \ |
| --output_dir=outputs/train/my_smolvla \ |
| --job_name=my_smolvla_training \ |
| --policy.device=cuda \ |
| --wandb.enable=true |
| ``` |
|
|
