Book series
The LLM Fine-Tuning Engineering Series
FINE-TUNING AN LLM IS NOT A SINGLE API CALL Most practitioners treat fine-tuning as a black box: upload a dataset, tweak a few hyperparameters, and hope for the best. This series...
3 books
The LLM Fine-Tuning Engineering Series
FINE-TUNING AN LLM IS NOT A SINGLE API CALL Most practitioners treat fine-tuning as a black box: upload a dataset, tweak a few hyperparameters, and hope for the best. This series replaces hope with a structured engineering workflow.
Fine-Tuning Large Language Models by Miles Thornton is a three-volume, framework-agnostic playbook for transforming general-purpose pretrained LLMs into reliable, domain-specific assistants. Each book tackles a critical stage of the lifecycle—from initial specialization to alignment and finally to production-scale infrastructure.
👉 Book 1: From Foundation Models to Domain-Specific AI Master systematic dataset engineering, supervised fine-tuning (SFT), and parameter-efficient methods like LoRA and QLoRA. Learn to evaluate memory, latency, and behavior consistency without abstract math.
This is the engineering discipline behind turning a base model into a task-specific expert. 👉 Book 2: RLHF, DPO, and Preference Optimization SFT teaches a model what to say; alignment teaches it how to behave.
Dive into the full post-SFT alignment stack: reward modeling, PPO stability, DPO, and modern variants like IPO, ORPO, and KTO. Build reproducible pipelines, design human evaluation loops, and debug reward hacking—all with practical intuition, not academic theory.
👉 Book 3: Efficient Training, Inference, and Production Deployment Training isn't just about GPUs—it's about managing bottlenecks....
Books in this series
Book 1
Fine-Tuning Large Language Models: From Foundation Models to Domain-Specific AI
Miles Thornton
Book 1
Fine-Tuning Large Language Models: From Foundation Models to Domain-Specific AI
Miles Thornton
Fine-tuning a large language model is not a single API call—it is a disciplined engineering workflow where data quality, parameter-efficient strategies, and systematic evaluation converge to produce production-ready domain AI. Yet many practitioners treat fin...
Book 2
Fine-Tuning Large Language Models: RLHF, DPO, and Preference Optimization
Miles Thornton
Book 2
Fine-Tuning Large Language Models: RLHF, DPO, and Preference Optimization
Miles Thornton
You have fine-tuned a large language model, but its responses still miss the mark on safety, tone, or user intent. Supervised fine-tuning teaches a model what to say; alignment teaches it how to behave. That gap is where this book lives. Fine-Tuning Large La...
Book 3
Fine-Tuning Large Language Models: Distributed Training, Inference, and Production
Miles Thornton
Book 3
Fine-Tuning Large Language Models: Distributed Training, Inference, and Production
Miles Thornton
Training a large language model isn't just about having powerful GPUs—it's about managing a cascade of bottlenecks: memory, communication, latency, and cost, each demanding deliberate trade-offs. Fine-Tuning Large Language Models is an engineering handbook t...