Downloads · 30 days
10
14% of all-time downloads
pi05_so101_expert_cosmos70_exp03_gate
Isk5434/pi05_so101_expert_cosmos70_exp03_gate
pi05_so101_expert_cosmos70_exp03_gate is a robotics model from Isk5434. 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. The card lists the license as apache-2.0.
π0.5 action-expert fine-tuned on SO-101 "vials to rack" — pick test-tube vials and place them in a rack.
All-time downloads
72
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%
Base models
Model card
From the Hugging Face model README
pi05_so101_expert_cosmos70_exp03_gate
π0.5 action-expert fine-tuned on SO-101 "vials to rack" — pick test-tube vials and place them in a rack.
Model details
| Base model | lerobot/pi05_base (Gemma-2B + 300M action expert) |
| Training mode | Expert-only (VLM backbone frozen, action expert fine-tuned) |
| Dataset | sreetz-nv/so101_teleop_vials_rack_left_cosmos_70 |
| Dataset size | 145 episodes (75 real teleop + 70 Cosmos-augmented) |
| Steps | 10 000 |
| Batch size | 16 |
| Learning rate | 2.5e-5 (cosine decay → 2.5e-6) |
| Final loss | 0.041 |
| Epochs | ~4.1 |
| Hardware | NVIDIA L40S 46 GB |
| Chunk size | 50 actions |
| Observation | ego (wrist) + external D455 RGB cameras + 6-DOF joint state |
Training curve
| Step | Loss |
|---|---|
| 500 | ~0.12 |
| 2 000 | ~0.072 |
| 6 000 | 0.046 |
| 10 000 | 0.041 |
W&B project: pi05-so101-vials
Usage
from lerobot.common.policies.pi05.modeling_pi05 import Pi05Policy
policy = Pi05Policy.from_pretrained("Isk5434/pi05_so101_expert_cosmos70_exp03_gate")
Or evaluate directly in Isaac Sim via the companion repo:
Isk5434/sim2real-so101
git clone --recurse-submodules https://github.com/Isk5434/sim2real-so101
bash run_webrtc.sh pi05
Training recipe
# Reproduce with train_pi05_so101.sh
STEPS=10000 BATCH=16 LR=2.5e-5 bash train_pi05_so101.sh expert_only cosmos
Full script with LoRA / full fine-tune / resume support:
train_pi05_so101.sh
Task
The SO-101 6-DOF robot arm grasps test-tube vials from a tray and places them upright in a rack. The model was trained on demonstrations collected via LeRobot teleoperation in Isaac Sim, with Cosmos video diffusion augmentation to expand the dataset.
Domain randomisation applied during training data collection:
- HDRI environment lighting
- Robot link colours
- Workspace mat texture
- Lightbox emission colour (USD shader)
- Camera extrinsics
- Vial / rack pose noise
Citation
If you use this checkpoint, please cite the base model and dataset:
@misc{pi05_so101_exp03,
author = {Ishikawa},
title = {π0.5 fine-tuned on SO-101 vials-to-rack},
year = {2026},
url = {https://huggingface.co/Isk5434/pi05_so101_expert_cosmos70_exp03_gate}
}
License
Apache-2.0
- Task
- Robotics
- Library
- lerobot
- License
- apache-2.0
- Languages
- en
- Created
- May 17, 2026
- Updated
- May 24, 2026