search

futo-org / android-keyboard

Offical FUTO Keyboard Issue Tracker and Source Mirror of https://gitlab.futo.org/keyboard/latinime
Other
647 stars 24 forks source link

The ability to determine when model fine tuning happens #399

Open a73s opened 2 months ago

a73s commented 2 months ago

Use Cases

It would be really nice to determine when predictive text model fine tuning happens, so that it wont drain my battery when I don't want it to.

Proposal

To either be able to manually start tuning, or schedule tuning at a particular time/when the phone is plugged in.

References

No response

haldi4803 commented 6 days ago

From the docs:

(Note: Finetuning is currently disabled by default as its effectiveness has not been properly evaluated, but the following applies if you enable it. Finetuning may not be stable) As you type things with the keyboard, your typed data is saved locally to temporary storage for later finetuning of the transformer LM. Finetuning is scheduled to run at least once every ~20 hours when your device is idle, plugged in and there's enough data. Under the hood, finetuning trains a LoRA adapter locally on your device, merges it with the original model and saves it. While the original data is deleted after finetuning, the finetuned model's weights may contain the data in some form or another, so we recommend avoiding sharing the finetuned model.