# Fine-tuning

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: fine tuning, fine-tune, finetune, finetuning, fine-tuned, fine tuned model, custom model

Extra training of an existing model on a smaller, narrower set of examples, so it suits one task or style. Not every [model provider](https://ecosystem.samcarlton.com/model-provider) offers it.

**For example:** A company fine-tunes a model on 2,000 of its past support replies. New drafts from that model match the company's tone.

## Connects to (10)

- [Training](https://ecosystem.samcarlton.com/training): Teaching an AI model by showing it a very large number of examples before anyone uses it.
- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [RAG](https://ecosystem.samcarlton.com/rag): Retrieval-augmented generation.
- [Prompt](https://ecosystem.samcarlton.com/prompt): The instructions or question you give an AI tool in everyday words.
- [LoRA](https://ecosystem.samcarlton.com/lora): Low-rank adaptation.
- [Overfitting](https://ecosystem.samcarlton.com/overfitting): When a model learns its training examples too closely, including their quirks, and then performs poorly on new data.
- [Distillation](https://ecosystem.samcarlton.com/distillation): Training a smaller model to copy the outputs of a larger one, so it keeps much of the quality while being cheaper and faster to run.
- [Few-shot prompting](https://ecosystem.samcarlton.com/few-shot-prompting): Including a few worked examples in a prompt so the model copies the pattern.
- [RLHF](https://ecosystem.samcarlton.com/rlhf): Reinforcement learning from human feedback.
- [FunctionGemma](https://ecosystem.samcarlton.com/functiongemma): A small Gemma model from Google tuned to turn plain requests into function calls, so an app or device can act on what a person asks.

Map view: https://ecosystem.samcarlton.com/fine-tuning