RACE_main_robocasa

SeonghoonYu/RACE_main_robocasa

RACE_main_robocasa is a robotics model from SeonghoonYu. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

pi0.5 checkpoints on RoboCasa H50 (25 single-stage atomic tasks, human teleop, ~55 demos/task, 1382 episodes). PyTorch (openpi PI0Pytorch) safetensors; norm stats included under assets/robocasa/robocasah50/.

Downloads · 30 days

Access

Public

Updated Sep 5, 2026

Repo size

36.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors36.9 GB · 100%

At a glance

Task: Robotics
License: mit
Access: Public
Created: Sep 5, 2026
Updated: Sep 5, 2026
SHA: 348d1228

Model card

From the Hugging Face model README

RACE_main_robocasa

pi0.5 checkpoints on RoboCasa H50 (25 single-stage atomic tasks, human teleop, ~55 demos/task, 1382 episodes). PyTorch (openpi PI0Pytorch) safetensors; norm stats included under assets/robocasa/robocasa_h50/.

folder	what	notes
`teacher_ac10_30k_pytorch/`	pi0.5 teacher, action_horizon 10, 30k steps from `pi05_base`, batch 64	PyTorch export (fp32) of the JAX checkpoint in `SeonghoonYu/RACE_Robocasa/teacher_ac10_30k`
`ft_vlmfreeze_h10_20k/`	plain fine-tune of the teacher, VLM (SigLIP + Gemma) frozen, action expert trained, horizon 10, 20k steps	model-only (no optimizer)
`ft_vlmfreeze_h15_20k/`	same, horizon 15	model-only
`ft_vlmfreeze_h20_20k/`	same, horizon 20	model-only

Fine-tune hyperparameters (all three): batch 64, constant LR 5e-5 (no warmup), AdamW, grad clip 1.0, bf16, 20k steps, initialised from the teacher.

RoboCasa eval (25 tasks x 50 trials, held-out object split B, open-loop chunk = horizon):

checkpoint	replan	success
teacher_ac10_30k	5	60.4%
teacher_ac10_30k	10	62.6%
ft_vlmfreeze_h10_20k	10	62.5%
ft_vlmfreeze_h15_20k	15	62.1%
ft_vlmfreeze_h20_20k	20	58.6%

Task: Robotics
License: mit
Created: Sep 5, 2026
Updated: Sep 5, 2026