metadata
license: apache-2.0
library_name: openpi
tags:
- robotics
- manipulation
- pi0.5
- openpi
- jax
- orbax
pipeline_tag: robotics
openpi-pi05-real01c-insert-marker-d1-ours-sobol-r0base-ft-iris
A Pi0.5 model fine-tuned using the OpenPI framework.
Model Details
| Property | Value |
|---|---|
| OpenPI config | pi05_sir_droid_finetune |
| Checkpoint step | 4999 |
| Training data | N/A |
| Precision | bfloat16 |
| Parameter size | ~6.7 GB |
| Source checkpoint | /iris/u/ankile/openpi-pi05-real01c/checkpoints/pi05_sir_droid_finetune/sir_real01c_ours_r0base_5k_bs32_iris/4999 |
| Hugging Face repo | ankile/openpi-pi05-real01c-insert-marker-d1-ours-sobol-r0base-ft-iris |
| W&B run | link |
| SLURM job ID | 15740314 |
Usage
Download and run inference
# Download checkpoint from HF Hub
huggingface-cli download ankile/openpi-pi05-real01c-insert-marker-d1-ours-sobol-r0base-ft-iris --local-dir <local_path>
# Run inference server
cd deps/openpi
uv run python scripts/serve_policy.py pi05_sir_droid_finetune \
--checkpoint-dir <local_path>
In-process inference (Python)
from openpi.training import config as openpi_config
from openpi.policies import policy_config as openpi_policy_config
train_config = openpi_config.get_config("pi05_sir_droid_finetune")
policy = openpi_policy_config.create_trained_policy(
train_config, "<local_path>"
)
result = policy.infer(obs_dict)
actions = result["actions"]
Checkpoint Format
Orbax format, all parameters in bfloat16.
├── _CHECKPOINT_METADATA
├── checkpoint_provenance.json
├── openpi_config.json
├── assets/
│ └── (normalization stats)
└── params/
└── (orbax checkpoint files)
License
Apache 2.0