Parameter-Efficient Fine-Tuning (PEFT/LoRA) — Fine-Tuning & Model Cus…

Adapting models efficiently on limited hardware

Steps in Parameter-Efficient Fine-Tuning (PEFT/LoRA)

Parameter-Efficient Fine-Tuning (PEFT) Fundamentals — beginner · Adapting a small number of parameters instead of the whole model
LoRA: Low-Rank Adaptation — beginner · How LoRA achieves efficient fine-tuning with low-rank matrices
QLoRA and Quantized Fine-Tuning — beginner · Combining quantization with LoRA to fine-tune on limited hardware
Choosing LoRA Rank and Target Modules — beginner · Key hyperparameters that affect PEFT quality and efficiency
Merging and Managing LoRA Adapters — beginner · Combining or swapping adapters for different tasks
Comparing PEFT Methods — beginner · LoRA versus other parameter-efficient techniques