LoRa fine-tune availability for Phi-4-mini-instruct

#15
by charliezjw - opened

Hi team,
Thanks for the amazing work. This model's prompt adherence ability is soooo much better than others!
I am wondering whether there is some suggested/recommended codebase for performing LoRa fine-tune on the model.
Thank you very much!

Hi @charliezjw , I would suggest checking out our example finetuning script: https://huggingface.co/microsoft/Phi-4-mini-instruct/blob/main/sample_finetune.py - it already contains example LoRa setup.

nguyenbh changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment