Parameter-efficient fine-tuning
2021
Train a small set of extra weights instead of the whole model. LoRA 2021, QLoRA 2023. Why thousands of fine-tunes exist on Hugging Face.
Also: LoRA, PEFT
Sources: AI4U editorial.
2021
Train a small set of extra weights instead of the whole model. LoRA 2021, QLoRA 2023. Why thousands of fine-tunes exist on Hugging Face.
Also: LoRA, PEFT
Sources: AI4U editorial.