README.md

---
library_name: lerobot
tags:
- diffusion-policy
- model_hub_mixin
- pytorch_model_hub_mixin
- robotics
---

This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Library: https://github.com/huggingface/lerobot
- Docs: [More Information Needed]


## Quickstart

The checkpoint in this repository is obtained by running [the Flower x LeRobot quickstart-example](https://github.com/adap/flower/tree/main/examples/quickstart-lerobot). This is the global model at round 35 which seemed to give good results.

### Install LeRobot

> [!NOTE]
> Install the version of LeRobot used by the example (the latest commit at the time the example was put together, mid Dec'24). You might want to try using a more recente version.

```shell
pip install "lerobot[pusht] @ git+https://github.com/huggingface/lerobot.git@96c7052777aca85d4e55dfba8f81586103ba8f61"
```

### Load checkpoint

```python
from lerobot.common.policies.diffusion.configuration_diffusion import DiffusionConfig
from lerobot.common.policies.diffusion.modeling_diffusion import DiffusionPolicy
from lerobot.common.datasets.lerobot_dataset import LeRobotDataset

dataset = LeRobotDataset("lerobot/pusht")

cfg = DiffusionConfig(down_dims=[256, 512, 1024])
policy = DiffusionPolicy(cfg, dataset_stats=dataset.stats)
policy.from_pretrained("jafermarq/lerobot123")

print(policy)
```