> This page is for version Nightly (default).
> For other versions, use one of these documentation indexes:
> - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt
> - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt
> - 0.7.0 · 26.10: https://docs.nvidia.com/nemo/automodel/v0.7/llms.txt
> - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt
> - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.

# praxis-1-droid

> Fine-tune Runway's praxis-1-droid world-action model with NeMo AutoModel: an expert-parallel recipe, its LoRA variant and a LIBERO before / after tutorial.

[Praxis-1](https://huggingface.co/runwayml/praxis-1-droid) is Runway's 27B world-action model: a sparse mixture-of-experts video
diffusion transformer (about 3B active parameters) that predicts the next frames of the robot's cameras, and an action expert that
reads those predictions and outputs the next chunk of end-effector actions. NeMo AutoModel has a checked-in recipe that fine-tunes
all of its weights on one node, and a tutorial that takes the single-arm checkpoint from 0 to 90 % success on a LIBERO task suite.

## Fine-Tune Praxis-1

Follow the [installation instructions](/nemo/automodel/get-started/installation) from a source checkout. The recipe also needs the reference
`praxis` package of the model builder on the Python path: it provides the Wan2.2 VAE and the Qwen3.5 text encoder that the policy
is trained with, and the closed-loop simulation client the tutorial evaluates with.

## Choose a Workflow

| Goal                                                              | Start Here                                                                                                                                                                                                                             |
| ----------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Fine-tune all weights on one 8-GPU node                           | Use the [recipe configuration](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/wam/praxis/praxis_1_libero.yaml).                                                                                                           |
| Convert LIBERO demonstrations, train, and evaluate before / after | Follow the [LIBERO tutorial](https://github.com/NVIDIA-NeMo/Automodel/blob/main/tutorials/praxis-1-libero/README.md).                                                                                                                  |
| Train adapters instead of all weights                             | Use the [LoRA configuration](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/wam/praxis/praxis_1_libero_lora.yaml); `python -m nemo_automodel.components.models.praxis.lora_export` merges the adapters into a checkpoint. |
| Prepare your environment                                          | Follow the [installation instructions](/nemo/automodel/get-started/installation).                                                                                                                                                                     |

### Configuration

| Setting  | Configuration                                                                                                                                                          |
| -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Hardware | 8 x H100 80 GB (one node)                                                                                                                                              |
| Strategy | FSDP2 with expert parallelism; ep_size=8, tp_size=1, pp_size=1, cp_size=1                                                                                              |
| Nodes    | 1                                                                                                                                                                      |
| Features | Checkpointing (consolidated checkpoint at every save), Activation checkpointing, Transformer Engine grouped experts with HybridEP token dispatch, fp32 optimizer state |
| Advanced | param_dtype=bfloat16, reduce_dtype=float32, dispatcher=hybridep                                                                                                        |

### Results

The tutorial fine-tunes the single-arm checkpoint on the LIBERO-Spatial demonstrations and evaluates it with the standard LIBERO
protocol, 500 paired episodes per checkpoint.

| Checkpoint                             | LIBERO-Spatial success |
| -------------------------------------- | ---------------------- |
| `runwayml/praxis-1-droid`, zero-shot   | 0/500                  |
| full fine-tune, 600 steps x 48 windows | 451/500 (90.2 %)       |
| LoRA, 600 steps x 48 windows           | 457/500 (91.4 %)       |

## Model Reference

### Model Architecture

| Property     | Value                                                 |
| ------------ | ----------------------------------------------------- |
| Task         | Robot policy (video prediction and action generation) |
| Architecture | `PraxisPolicy`                                        |

### Available Models

* [`runwayml/praxis-1-droid`](https://huggingface.co/runwayml/praxis-1-droid): the single-arm checkpoint; the recipe reads its `config.json` for the cameras, the action space and the normalization.

The recipe supports the single-arm embodiment; the bimanual checkpoint has a different action space and camera layout.

## Related Resources

* [LIBERO before / after tutorial](https://github.com/NVIDIA-NeMo/Automodel/blob/main/tutorials/praxis-1-libero/README.md)
* [Praxis-1 on Hugging Face](https://huggingface.co/runwayml/praxis-1-droid)