Downloads · 30 days
34
40% of all-time downloads
piper-pi0.5-hanyang-v2
leejaehot/piper-pi0.5-hanyang-v2
piper-pi0.5-hanyang-v2 is a robotics model from leejaehot. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot.
Pi0.5 policy for a Piper single-arm robot, fine-tuned from lerobot/pi05base on the HYU white-box normalized 100-demo dataset.
All-time downloads
84
Public
Parameters
4.1B
9.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.4 GB · 100%
Parameter types
How the weights are stored.
BF163.6B · 87%
Model card
From the Hugging Face model README
Piper Pi0.5 — Hanyang v2
Pi0.5 policy for a Piper single-arm robot, fine-tuned from lerobot/pi05_base on the HYU white-box normalized 100-demo dataset.
Model details
| Field | Value |
|---|---|
| Policy | Pi0.5 |
| Robot | Piper |
| Dataset | oms524/place_spam_into_the_white_box_30hz_normalized |
| Training steps | 20,000 |
| Action chunk size | 50 |
| State/action normalization | Quantiles |
| Cameras | Front, right camera |
| Seed | 1000 |
Usage
Use this repository as the policy path in a LeRobot inference or rollout command:
--policy.path=leejaehot/piper-pi0.5-hanyang-v2
This repository contains model weights and policy processors. Training-state files are not included.
- Task
- Robotics
- Library
- lerobot
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026