| --- |
| license: apache-2.0 |
| tags: |
| - robotics |
| - vla |
| - vision-language-action |
| - pi-05 |
| - nut_thread |
| - sim |
| pipeline_tag: robotics |
| --- |
| # FIRe-VLA-PI05-NutThread-Sim |
|
|
| <!-- TODO: FIRe project one-line description and paper/code links --> |
|
|
| A **PI05** vision-language-action policy fine-tuned for the **Nut threading** contact-rich |
| robotic assembly task (**Sim** domain), part of the FIRe model suite. |
|
|
| - **Framework:** PI05 |
| - **Task:** Nut threading (`nut_thread`) |
| - **Domain:** Sim |
| - **Checkpoint:** inference-ready (9999 steps) |
|
|
| ## Usage |
|
|
| ```bash |
| # Requires openpi: https://github.com/Physical-Intelligence/openpi |
| huggingface-cli download bhe1004/FIRe-VLA-PI05-NutThread-Sim --local-dir ./FIRe-VLA-PI05-NutThread-Sim |
| ``` |
| ```python |
| # Point the openpi trained-policy loader at the downloaded checkpoint dir. |
| # The repo holds params/ + assets/ (norm stats); train_state/ was dropped |
| # since it is only needed to resume training. |
| from openpi.policies import policy_config |
| policy = policy_config.create_trained_policy(config, "./FIRe-VLA-PI05-NutThread-Sim") |
| ``` |
|
|
| ## Related |
| - Training data: [`bhe1004/FIRe-VLA-PI05-NutThread-Sim`](https://huggingface.co/datasets/bhe1004/FIRe-VLA-PI05-NutThread-Sim) |
|
|
