Dataset used?
#2
by
qingy2024
- opened
Hi, thanks for the great work!
Do you mind sharing what dataset you used to fine tune this model?
Hoo, I didn't update it in the model card?. I'll update it as soon as possible.
By the way, Phi-4o-SFT was trained with following entries ;
-OpenO1-SFT-Ultra
-QWQ-LONGCOT-500K
-NuminaMath-CoT
-GSM8K
Oh thanks!
By the way, is it a full parameter fine tune or did you use PEFT methods like LoRA?
Full Param's FT
prithivMLmods
changed discussion status to
closed