openpi icon indicating copy to clipboard operation
openpi copied to clipboard
verified publisher icon Physical-Intelligence

How to perform LoRA fine-tuning

Open Addog666 opened this issue 3 months ago • 0 comments

XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 uv run scripts/train.py mytest --exp-name=my_experiment --overwrite

This command seems to perform full fine-tuning. How can I modify it to perform LoRA fine-tuning instead?

Addog666 avatar Oct 23 '25 06:10 Addog666