OpenPI Fine-tuned Model
This model was fine-tuned using OpenPI.
Training Details
- Global Step: 5000
- Experiment Name: droid-finetune-cube-stacking
- Learning Rate: N/A
- Batch Size: 32
Usage
from openpi.models_pytorch.pi0_pytorch import PI0Pytorch
from safetensors.torch import load_file
from huggingface_hub import hf_hub_download
# Download model weights
model_path = hf_hub_download(repo_id="your-repo-id", filename="model.safetensors")
state_dict = load_file(model_path)
# Load model (adjust config as needed)
model = PI0Pytorch(...)
model.load_state_dict(state_dict)