fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
- Version
- 1.0.0
- License
- MIT
Pinned to revision df088027ff23, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/fine-tuning-serving-openpi/SKILL.md
- skills/fine-tuning-serving-openpi/references/checkpoints-and-env-map.md
- skills/fine-tuning-serving-openpi/references/config-recipes.md
- skills/fine-tuning-serving-openpi/references/for-hpc-cluster-users.md
- skills/fine-tuning-serving-openpi/references/pytorch-gotchas.md
- skills/fine-tuning-serving-openpi/references/remote-client-pattern.md
- skills/fine-tuning-serving-openpi/references/training-debugging.md
Every link opens the file at its source, pinned to the revision this page describes.