Fine-Tuning and Model Optimization

A practical guide to adapting foundation models without large budgets. Covers when to fine-tune versus prompt, dataset curation, full fine-tuning, PEFT, LoRA and QLoRA, quantization (NF4, GPTQ, AWQ, GGUF), distillation, instruction tuning, evaluation, serving with vLLM, MLOps, and domain case studies. Fourteen chapters with real Python code and the failure modes that quietly destroy fine-tuning pr...