MLX Full Fine Tune (not Lora) without freezing weights

#15
by Goblinztech - opened
MLX Community org

I found sources only how to do finetuning creating adapters. My q is, any source of info for Full Fine tuning?

MLX Community org

Hi, @Goblinztech ! The full fine-tune has been implemented, but you do it through the mlx_lm.lora script, as indicated here.

image.png

Sign up or log in to comment