The Fine-Tuning Handbook
Fine-tuning is badly served by the writing about it. Half of it is marketing, the other half is a paper. This is the middle: what fine-tuning does, when it beats a longer prompt, which method to reach for, and how to tell whether the run actually worked.
Put together by the team building Fernfly, out of the runs that went wrong before the ones that went right.
The honest decision tree. Most of the time the answer is no, and this says when.
What changes inside the model, and what stubbornly does not.
Full fine-tuning, LoRA and the rest of the family, and what each one costs you.
Instruction tuning, preference methods, and getting a model to act rather than answer.
Datasets, hyperparameters, hardware, and the parts nobody writes down.
How to tell a model that works from one that only looks like it does.
Overfitting, catastrophic forgetting, leaky splits, and other ways runs quietly go wrong.
Worked end-to-end setups you can copy for common tasks.
The terms, formats and numbers worth keeping to hand.
How this was made. The team set the outline, chose the claims and the worked examples, and checked them against our own training runs. The prose was drafted with AI assistance.
Get the handbook
Enter the unlock code you were given and we'll email it to you, in PDF and EPUB.
No code? Read the blog in the meantime.