liveBook · Manning

Fine-tuning

As explained in AI Agents in Action

A fine-tuned model is a pretrained model further trained on additional data for a narrower behavior or domain.

Fine-tuning refines a model’s training to better match a particular use case or domain. It can make a model more relevant for a domain-specific agent. section 2.0 section 2.4

From general training to chat

ChatGPT is trained on public-internet content, then fine-tuned using several strategies, including reinforcement learning with human feedback (RLHF). section 2.0

Figure 2.2 The main elements that describe an LLM
figure

See how fine-tuning fits alongside data and architecture as an element of an LLM. section 2.0

How AI Agents in Action covers it

How deep it goes
Defines use-case refinement and gives ChatGPT and domain-selection examples, without detailing training procedures.
Examples
Uses ChatGPT’s public-internet training and RLHF, and considers smaller fine-tuned models for domain-specific agents.
What you can do after
Evaluate whether a domain-specific fine-tuned model may suit an agent as well as or better than a larger general model.
How it connects
Relates fine-tuning to LLM training data, model architecture, RLHF, and domain-specific agents.

Also explained in

Compare how 52 books explain fine-tuning →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Agents in Action. The section links point to the parts of the book it draws on.