How to do fine tuning with distilled data

I would like to do fine tuning with distilled data.
The finetune_demo.sh does not seem to show how to do this.
I already have .cif files of distillation data.
I'm a newbie, so sorry if I'm looking in the wrong place.

Start with finetune_demo.sh and trace how the fine-tuning entry point handles input data. Verify whether the existing workflow accepts the reported .cif distillation files, then document the required steps or record what support is missing; done means a newcomer can follow the documented workflow.

Written by the indexing model from the issue text.