README.md

---
datasets: HuggingFaceVLA/libero
library_name: lerobot
license: apache-2.0
model_name: pi05
pipeline_tag: robotics
tags:
- pi05
- lerobot
- robotics
---

# Model Card for pi05

<!-- Provide a quick summary of what the model is/does. -->


**π₀.₅ (Pi05) Policy Finetuned with Quantile normalization**

This model which come from the Pytorch conversion script of openpi and their `pi05_libero` model, has been finetuned for 6k steps on 8x H100 GPU's.

π₀.₅ is a Vision-Language-Action model with open-world generalization, from Physical Intelligence. The LeRobot implementation is adapted from their open source OpenPI repository.

**Model Overview**

π₀.₅ represents a significant evolution from π₀, developed by Physical Intelligence to address a big challenge in robotics: open-world generalization. While robots can perform impressive tasks in controlled environments, π₀.₅ is designed to generalize to entirely new environments and situations that were never seen during training.

For more details, see the [Physical Intelligence π₀.₅ blog post](https://www.physicalintelligence.company/blog/pi05).


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 src/lerobot/scripts/train.py \
    --dataset.repo_id=your_dataset \
    --policy.type=pi05 \
    --output_dir=./outputs/pi05_training \
    --job_name=pi05_training \
    --policy.repo_id=your_repo_id \
    --policy.pretrained_path=lerobot/pi05_libero_finetuned_quantiles \
    --policy.compile_model=true \
    --policy.gradient_checkpointing=true \
    --wandb.enable=true \
    --policy.dtype=bfloat16 \
    --steps=3000 \
    --policy.scheduler_decay_steps=3000 \
    --policy.device=cuda \
    --batch_size=32
```

---

## Model Details

- **License:** apache-2.0