Bahree-HI (1)1200×1505 73.7 KB

Amit Bahree, Weehyong Tok

A lot of teams are past the “can we call an LLM API?” stage and are now running into harder questions: when is prompting enough? When does RAG make more sense? When is fine-tuning actually worth the time, data work, and evaluation burden? And once you do customize a model, how do you know it got better without quietly making it worse somewhere else?

That’s the space this book is meant to help with. It’s a practical guide to adapting LLMs for real applications, covering the decision points around prompting, retrieval, fine-tuning, distillation, alignment, evaluation, safety, and deployment tradeoffs. The goal isn’t to sell fine-tuning as the answer to everything, but to help readers understand where it fits and how to approach it responsibly when it does.

The book is now available in MEAP, so early readers can read it while it’s being written and send feedback that may help shape the final version.

• Full details: LLM Customization and Fine-Tuning - Amit Bahree, Weehyong Tok

Don’t forget you can get 45% off with your Devtalk discount! Just use the coupon code “devtalk.com” at checkout