LoRA/QLoRA (peft/trl or unsloth) on identical data, cloud/rented GPU. Same recipe as ScribeAgent / distil labs LFM2.5 fine-tune.
LoRA/QLoRA (peft/trl or unsloth) on identical data, cloud/rented GPU. Same recipe as ScribeAgent / distil labs LFM2.5 fine-tune.