Daniel & Friends / Glossary / Fine-tuning
AI and automationFine-tuning
Fine-tuning is further training of an already trained model on your own examples so that it specialises in a style or a task. Unlike RAG, it changes the model itself.
Daniel Votruba ·
In practice
Try a good prompt and RAG first. Fine-tuning pays off when you need a stable style or format at high volume.
Read more: AI & automation
Related terms
- RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.
- Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
- Prompt engineering: Prompt engineering is the design and testing of instructions for a model: choosing the role, context, examples and answer format so that the output is reliably usable.
More terms in the group AI and automation
Foundation model · Few-shot and zero-shot prompting · Function calling (tool use) · Explainable AI (XAI) · Generative AI · EU AI Act · Grounding · Embedding · Guardrails · Diffusion models · Hallucination · Deep learning · Human in the loop · Deepfake and synthetic media · Inference and latency · Custom GPTs and projects · Jailbreak (AI) · Copilot (AI assistant) · Context window · Machine learning (ML) · Computer vision · MCP (Model Context Protocol) · ChatGPT Ads · Model bias (AI bias)
Terms in practice
Need help putting them to work?
Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.
Book a call