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