Finetuning

2 pages

AI Engineering source
*AI Engineering* — Chip Huyen
Finetuning concept
When to finetune vs RAG; memory bottleneck; quantisation (FP32→INT4); PEFT; LoRA (low-rank decomposition, rank, alpha, multi-LoRA serving); QLoRA; model merging (task arithmetic, TIES/DARE, frankenmerging); finetuning tactics