| pipeline_tag: robotics | |
| tags: | |
| - lerobot | |
| library_name: lerobot | |
| SmolVLA: A vision-language-action model for affordable and efficient robotics | |
| [Paper](https://huggingface.co/papers/2506.01844) | |
| [Code](https://github.com/huggingface/lerobot) | |
| Designed by Hugging Face. | |
| This model has 450M parameters in total. | |
| You can use inside the [LeRobot library](https://github.com/huggingface/lerobot). | |
| 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=danaaubakirova/svla_so100_task1_v3 \ | |
| --batch_size=64 \ | |
| --steps=200000 | |
| ``` | |
| Example of finetuning the smolvla neural network with pretrained VLM and action expert | |
| intialized from scratch: | |
| ```bash | |
| python lerobot/scripts/train.py \ | |
| --policy.type=smolvla \ | |
| --dataset.repo_id=danaaubakirova/svla_so100_task1_v3 \ | |
| --batch_size=64 \ | |
| --steps=200000 | |
| ``` | |
| Example of using the smolvla pretrained model outside LeRobot training framework: | |
| ```python | |
| policy = SmolVLAPolicy.from_pretrained("lerobot/smolvla_base") | |
| ``` |