liveBook · Manning

Fine-tuning

Also called fine-tune, finetuning

Fine-tuning is the continued training of a pretrained model on targeted data or objectives to adapt its parameters or behavior to a task, domain, or use.

How 52 Manning books explain it

Building Specialized AI Systems

Fine-tuning is the process of adapting a pretrained model to a related task or specialized domain by continuing training with targeted data.

How it is used
Builds specialized language models for precision-demanding, domain-specific tasks where general-purpose behavior is inadequate.
How deep it goes
Explains transfer learning, prompt-completion training, iterative workflow, and parameter-efficient methods; defers Transformer internals and method selection details.
Examples
Uses customer-support ticket classification, credit-risk assessment, and financial analyst-report summarization with structured input-output pairs.
What you can do after
Build it from scratch by selecting a base model, preparing examples, training an adapter, evaluating results, and deploying iteratively.

Read how Building Specialized AI Systems explains fine-tuning →

LLMs in Production

Fine-tuning is the process of continuing model training on task-specific data to adapt a pretrained model to a particular behavior or domain.

How it is used
Uses fine-tuning to specialize pretrained models for tasks, domains, and desired behaviors without training from scratch.
How deep it goes
Explains model selection, data preparation, training loops, evaluation, resource trade-offs, and decisions about retraining.
Examples
Illustrates instruction tuning with translation and fine-tunes GPT-2 on a text dataset using Python training tools.
What you can do after
Apply fine-tuning via Hugging Face Transformers to adapt a pretrained model to a prepared dataset.

Read how LLMs in Production explains fine-tuning →

Natural Language Processing in Action, Second Edition

Fine-tuning is the continued training of a pretrained model on a narrower dataset or task so its parameters adapt to that target domain or behavior.

How it is used
Adapts pretrained transformers to classification tasks and domain-specific text generation.
How deep it goes
Explains end-to-end BERT fine-tuning and walks through dataset preparation, training, evaluation, and a GPT-2 Trainer workflow.
Examples
Uses labeled toxic comments for multi-label classification and a sentence corpus to adapt GPT-2 generation.
What you can do after
Apply it via Simple Transformers and Hugging Face Trainer to train and evaluate pretrained models.

Read how Natural Language Processing in Action, Second Edition explains fine-tuning →

Generative AI in Action

Task-specific fine-tuning is the adaptation of a pretrained model using data targeted at a particular task.

How it is used
Positions fine-tuning as a later enterprise adaptation option for specialized tasks, alongside prompt engineering and retrieval-augmented generation.
How deep it goes
Walks through model selection, data preparation, training, evaluation, and deployment, with a high-level explanation of LoRA.
Examples
Uses a Microsoft Teams emoji responder and JSONL prompt–response examples to demonstrate adaptation.
What you can do after
Apply it via the Azure OpenAI Python SDK or Azure AI Studio, then evaluate the adapted model against a baseline.

Read how Generative AI in Action explains fine-tuning →

Software Testing with Generative AI

Fine-tuning is the process of adapting a pretrained model to a task or domain by training it further on targeted data.

How it is used
Deploys targeted training to embed testing or business-domain context into an LLM’s responses.
How deep it goes
Explains goals, data preparation, tokenization, tuning, metrics, testing, and iteration, while deferring many implementation nuances.
Examples
Uses London travel responses, project-code instruction records, Axolotl commands, and loss and learning-rate logs.
What you can do after
Operate/configure Axolotl to prepare data, run a LoRA fine-tune, and test the resulting domain-specific model.

Read how Software Testing with Generative AI explains fine-tuning →

The Art of AI Product Development

Fine-tuning is adapting a pretrained model by training it further on task- or domain-specific data.

How it is used
Addresses persistent domain, task, and instruction-following gaps in language-model products when prompting or retrieval alone falls short.
How deep it goes
Explains model selection, dataset creation, and evaluation for three objectives, while leaving technical engineering challenges to the engineering team.
Examples
Uses content-app topic classification and draft revision, plus sustainability reporting with Llama 3.2, to illustrate specialization.
What you can do after
Evaluate whether to pursue fine-tuning and guide model selection, task-specific data creation, and real-world evaluation.

Read how The Art of AI Product Development explains fine-tuning →

Reinforcement Learning from Human Feedback

Fine-tuning is further training of a pretrained model on a task-specific or behavior-specific objective.

How it is used
Establishes instruction-following behavior as a foundation for language-model post-training and RLHF.
How deep it goes
Explains supervised loss masking, data and batch choices, and KL-regularized RL objectives, with comparisons of generalization and forgetting.
Examples
Contrasts boiling-point responses and describes Tülu 3 training, tool trajectories, and arithmetic and navigation distribution-shift tests.
What you can do after
Operate/configure instruction tuning by choosing response masking, batch sizes, and training data suited to downstream tasks.

Read how Reinforcement Learning from Human Feedback explains fine-tuning →

Deep Learning with R, Third Edition

Fine-tuning is the continued training of a pretrained model, typically with a small learning rate, to adapt its learned representations to a new task.

How it is used
Adapts pretrained image and language models to classification or desired instruction-following behavior.
How deep it goes
Works through freezing, unfreezing, training, and evaluation; defers the effects of batch normalization on fine-tuning.
Examples
Uses Xception for cats versus dogs, RoBERTa for IMDb sentiment, and Gemma with instruction–response pairs.
What you can do after
Apply fine-tuning via R/Keras to a pretrained image classifier and a RoBERTa sentiment classifier.

Read how Deep Learning with R, Third Edition explains fine-tuning →

Deep Learning with Python, Third Edition

Adapting a pretrained model to a new task by continuing training, usually with a smaller learning rate or on additional data.

How it is used
Adapts pretrained vision and language models to classification and instruction-following tasks.
How deep it goes
Provides training workflows and code for vision and language models, while deferring batch normalization’s effect on fine-tuning.
Examples
Uses Xception on cats and dogs, RoBERTa on IMDb reviews, and Gemma with instruction-response pairs.
What you can do after
Apply it via Keras and KerasHub to adapt pretrained classifiers and prepare instruction-response training data.

Read how Deep Learning with Python, Third Edition explains fine-tuning →

Build a Large Language Model (From Scratch)

Further training of a pretrained model on a smaller task-specific dataset to improve downstream performance.

How it is used
Adapts foundation models for domain-specific or downstream tasks after broad language pretraining.
How deep it goes
Explains the two-stage workflow and model-loading step, but defers detailed optimization and parameter-update mechanics.
Examples
Uses labeled instruction-response data, sentence transformation, personal assistants, and text classifiers as concrete applications.
What you can do after
Apply it to adapt pretrained GPT models for instruction following or classification with smaller task-specific datasets.

Read how Build a Large Language Model (From Scratch) explains fine-tuning →

AI-Powered Search

Fine-tuning is additional training of a pretrained model on task-specific data to adapt its behavior or performance.

How it is used
Adapts pretrained models for domain-specific search, semantic similarity, and question answering.
How deep it goes
Walks through dataset preparation, model fine-tuning, holdout evaluation, and reader integration, while distinguishing weight updates from inference-time prompting.
Examples
Uses Stack Exchange outdoors question-answer pairs and the Semantic Text Similarity Benchmark as domain and similarity examples.
What you can do after
Apply fine-tuning to a question-answering model and use the Transformers pipeline to evaluate and deploy its reader.

Read how AI-Powered Search explains fine-tuning →

Retrieval Augmented Generation, The Foundational Ideas

Fine-tuning is further training of a pretrained model on task-specific or domain-specific data.

How it is used
Adapts RAG retrieval and answer behavior to task-specific or domain-specific failures after pretrained components provide a starting point.
How deep it goes
Explains supervised objectives, which components update or stay frozen, and failure-driven training recipes; stops short of a full training implementation.
Examples
Uses REALM and canonical RAG training stages, a FiD synthesis failure, and RAFT examples mixing answer-bearing passages with distractors.
What you can do after
Evaluate/understand when to retain naive RAG and when to target the retriever, reader, or generator with fine-tuning.

Read how Retrieval Augmented Generation, The Foundational Ideas explains fine-tuning →

Local Image Generation

Fine-tuning is the continued training of a pretrained model on additional data or a specialized task to adapt its behavior.

How it is used
Uses extra training to turn a base diffusion model into a custom checkpoint for improved image-generation goals.
How deep it goes
Walks through data, OneTrainer setup, checkpoints, epoch-by-epoch samples, and result analysis without detailing training internals.
Examples
Compares monster, space-man, and cowboy prompts across training epochs, including grasshopper, sandworm, and crab outputs.
What you can do after
Operate/configure it with OneTrainer to create and evaluate an SD1.5 custom checkpoint from image-and-label training data.

Read how Local Image Generation explains fine-tuning →

Transfer Learning for Natural Language Processing

Fine-tuning is adapting a pretrained model to a new task by updating some or all of its parameters.

How it is used
Adapts pretrained models to new NLP tasks, languages, and domains using target data.
How deep it goes
Explains layer freezing and learning-rate strategies, then demonstrates model adaptation and evaluation; discusses ULMFiT techniques before implementing them elsewhere.
Examples
Uses a tabular column-type classifier and BERT fine-tuning on the GLUE STS-B sentence-similarity task.
What you can do after
Apply it via transformers scripts to a GLUE task or suitably formatted custom data, and inspect saved evaluation results.

Read how Transfer Learning for Natural Language Processing explains fine-tuning →

Grokking AI Applications

Fine-tuning is additional training of a pretrained model on more specific data or objectives to adapt its behavior.

How it is used
Adapts pretrained language models for specific tasks, domains, instructions, and conversational behavior.
How deep it goes
Explains supervised examples and parameter adjustment through backpropagation-like passes, but does not detail implementation procedures or training configurations.
Examples
Uses GPT-3, ChatGPT dialogue refinement, prompt-completion pairs, and specialized medical knowledge as examples.
What you can do after
Apply supervised fine-tuning to move a pretrained model toward desired task, domain, instruction-following, or dialogue outputs.

Read how Grokking AI Applications explains fine-tuning →

How Large Language Models Work

Fine-tuning is an additional training stage that adapts a pretrained model to a particular task or behavior using a smaller, task-relevant dataset.

How it is used
Uses a second training stage to constrain an LLM’s behavior for instruction following, domain knowledge, or application-specific goals.
How deep it goes
Explains SFT mechanics and RLHF objectives, but stops short of detailed optimization, implementation, and adversarial-machine-learning treatment.
Examples
Uses car sales, medical records, legal transcripts, repair manuals, code repositories, coding questions, and symbolic mathematics.
What you can do after
Apply it via SFT or RLHF to adapt a pretrained model, while selecting task data and checking privacy, reliability, and output risks.

Read how How Large Language Models Work explains fine-tuning →

Time Series Forecasting Using Foundation Models

Fine-tuning is additional training of a pretrained model on task- or domain-specific data by updating some or all of its parameters.

How it is used
Specializes foundation forecasting models for a target dataset when zero-shot predictions may not be accurate enough.
How deep it goes
Explains parameter depth, training budgets, losses, validation, and overfitting, but does not disclose TimeGPT’s exact tuned-parameter counts.
Examples
Uses N-BEATS, TimeGPT, Lag-Llama, and Chronos on store-sales forecasting experiments.
What you can do after
Diagnose with validation metrics whether adapting a pretrained forecaster improves accuracy enough to justify its computational cost.

Read how Time Series Forecasting Using Foundation Models explains fine-tuning →

LLM Customization and Fine-Tuning

Further training a pretrained model on task- or domain-specific data to change its behavior.

How it is used
Positions fine-tuning as an enterprise adaptation option for behavior gaps, including domain conventions and brand voice.
How deep it goes
Develops a decision path from prompting to fine-tuning, with evaluation, cost crossover, and deployment considerations.
Examples
Uses earnings transcripts, Korean customer-service conversations, and clinical question-answer pairs to illustrate adaptation choices.
What you can do after
Evaluate whether fine-tuning fits a behavior gap and compare it with prompting or retrieval using held-out examples and cost assumptions.

Read how LLM Customization and Fine-Tuning explains fine-tuning →

Deep Learning with PyTorch, Second Edition

The process of adapting a pretrained model to a new task by continuing training on task-specific data.

How it is used
Uses fine-tuning to adapt pretrained models to task-specific data, including automatic segmentation of CT nodule candidates.
How deep it goes
Defines fine-tuning and works through dataset preparation, pretrained model setup, training, monitoring, and inference.
Examples
Uses CT slices and Segment Anything-generated masks to fine-tune SegFormer, and suggests a pretrained Vision Transformer exercise on CIFAR-10.
What you can do after
Apply it via Hugging Face Transformers to train a SegFormer for nodule segmentation and inspect predictions on unseen scans.

Read how Deep Learning with PyTorch, Second Edition explains fine-tuning →

Introduction to Generative AI, Second Edition

Fine-tuning is adapting a pretrained model through continued training for a particular task or behavior.

How it is used
Adapts pretrained language models to specific tasks, instruction-following, safety behavior, and tool use.
How deep it goes
Explains supervised examples and next-token prediction at an overview level, without a training procedure or implementation details.
Examples
Uses product-review sentiment ratings, safe responses to unsafe inputs, and Toolformer’s API calls as examples.
What you can do after
Evaluate and understand how fine-tuning steers a pretrained model and why example quality and labor conditions matter.

Read how Introduction to Generative AI, Second Edition explains fine-tuning →

LLM Evaluation and Alignment, The Foundational Ideas

Fine-tuning is the additional training of a pretrained model on a task-specific or domain-specific dataset.

How it is used
Uses supervised fine-tuning to turn pretrained text completion into instruction following and establish a starting policy for alignment.
How deep it goes
Explains training objectives, demonstration formats, data preparation, iteration, and imitation limits without detailing a fine-tuning implementation.
Examples
Illustrates SFT with earnings-report summaries, labeler-written demonstrations, and responses revised by an AI critic.
What you can do after
Evaluate how demonstration quality and coverage affect fine-tuning, and plan a critique-revise, train, and test cycle.

Read how LLM Evaluation and Alignment, The Foundational Ideas explains fine-tuning →

Data Analysis with LLMs

Fine-tuning is the process of further training an existing model on task-specific examples to adapt its behavior to a particular task.

How it is used
Specializes an existing model for a specific analysis task when simpler optimization methods may not suffice.
How deep it goes
Works through labeled-data format, model use, and a cost comparison, without showing a fine-tuning job submission in the supplied excerpts.
Examples
Uses labeled movie reviews, a JSON-lines chat interaction, and a ten-review accuracy and token-cost test.
What you can do after
Apply it via OpenAI chat models: prepare labeled examples, use a fine-tuned model ID, and assess whether its results justify its costs.

Read how Data Analysis with LLMs explains fine-tuning →

Build a Text-to-Image Generator (from Scratch)

Fine-tuning is adapting a pretrained model to a new task by updating selected parameters, often only the task-specific output layers.

How it is used
Applies pretrained models to specialized tasks when training from scratch would require excessive data, time, or computation.
How deep it goes
Explains freezing, head replacement, training, validation, and early stopping, but focuses on output-head adaptation rather than full-network retraining.
Examples
Uses ResNet50 to classify sample images, then adapts it to distinguish real images from AI-generated deepfakes.
What you can do after
Apply it via PyTorch and torchvision to build a specialized image classifier with frozen pretrained features and a trainable task head.

Read how Build a Text-to-Image Generator (from Scratch) explains fine-tuning →

Domain-Specific Small Language Models

Training a pretrained model further on task- or domain-specific data to adapt it to a narrower use case.

How it is used
Adapts pretrained models to narrower tasks or domains without developing a model from scratch.
How deep it goes
Works through data preparation, full-parameter training, and question-answering inference; contrasts full fine-tuning with parameter-efficient methods.
Examples
Demonstrates DistilBERT question answering and GPT-2 code generation; identifies antibody generation as a domain-specific application.
What you can do after
Apply it via Hugging Face Transformers to prepare a dataset, train a pretrained question-answering model, and extract an answer span.

Read how Domain-Specific Small Language Models explains fine-tuning →

Build a DeepSeek Model (From Scratch)

Fine-tuning is continued training of a pretrained model on a targeted dataset to adapt its behavior or capabilities.

How it is used
Uses supervised fine-tuning to shape assistant behavior and transfer teacher reasoning into smaller models.
How deep it goes
Explains dataset preparation and placement in training pipelines, but does not detail an SFT implementation.
Examples
Compares SFT on teacher-generated traces with direct RL on the same Qwen2.5-32B architecture.
What you can do after
Evaluate supervised fine-tuning’s role and trade-offs in staged post-training and teacher–student distillation.

Read how Build a DeepSeek Model (From Scratch) explains fine-tuning →

Building Reliable AI Systems

Fine-tuning is the adaptation of a pretrained model by further training it, typically on task- or domain-specific data.

How it is used
Adapts pretrained models when prompting or retrieval alone cannot deliver sufficient domain-specific behavior.
How deep it goes
Details data preparation, model selection, managed training jobs, monitoring, and evaluation, alongside cost and reliability trade-offs.
Examples
Uses a branded e-commerce support assistant, medical exam performance, and biased customer-service logs to illustrate applications and risks.
What you can do after
Apply it via the OpenAI Python SDK to upload examples, run and monitor a fine-tuning job, and use the resulting model.

Read how Building Reliable AI Systems explains fine-tuning →

Understanding AI

Fine-tuning is the continued training of a pretrained model on a smaller, task- or behavior-specific dataset to adapt its outputs.

How it is used
Transforms a prediction-focused foundation model into a conversational assistant that interprets input as instructions.
How deep it goes
Explains curated prompt-response training and its behavioral effect, while deferring training mathematics and update mechanics.
Examples
Contrasts a concert-review summary prompt treated as text continuation with one answered as an assistant request.
What you can do after
Evaluate/understand why an assistant responds to a prompt differently from a raw foundation model.

Read how Understanding AI explains fine-tuning →

Rearchitecting LLMs

Fine-tuning that adapts a model for a particular specialization or domain.

How it is used
Adapts model behavior to domain tasks and output formats, optionally after pruning and knowledge recovery.
How deep it goes
Develops an adapter-training workflow from model loading and configuration through training, merging, and evaluation baselines.
Examples
Uses clinical JSON extraction and a three-function calling specialist to illustrate behavioral adaptation.
What you can do after
Apply it via LoRA to specialize a model for function calling and merge the trained adapter.

Read how Rearchitecting LLMs explains fine-tuning →

Data Storytelling with Altair and AI

Fine-tuning is the additional training of a pretrained machine-learning model on targeted data to adapt its parameters to a task or domain.

How it is used
Adapts LLM-generated data-story titles, annotations, and commentaries to particular audiences, scenarios, and domains.
How deep it goes
Defines targeted retraining and walks through dataset construction, JSONL conversion, API job creation, and generation without explaining LLM internals.
Examples
Demonstrates audience-specific titles and commentary using household chores and popular-sports percentages, plus CSV-to-JSONL conversion.
What you can do after
Apply it via the OpenAI API to train and call an audience-specific model for new data commentary.

Read how Data Storytelling with Altair and AI explains fine-tuning →

Starting Data Analytics with Generative AI and Python

Fine-tuning is the further training of a pretrained model on targeted data to adapt its behavior or performance.

How it is used
Adapts pretrained language models to nuanced or domain-specific NLP tasks when labeled-data resources are limited.
How deep it goes
Explains benefits, requirements, alternatives, and overfitting risk, but stops short of procedural training details.
Examples
Uses BERT on Hugging Face as an NLP fine-tuning example and contrasts it with zero-shot learning and training from scratch.
What you can do after
Evaluate whether adapting a pretrained model suits a task by weighing data quality, model relevance, resources, and overfitting risk.

Read how Starting Data Analytics with Generative AI and Python explains fine-tuning →

Transformers in Action

Fine-tuning is the adaptation of a pretrained model by further optimizing its parameters for a specific task or behavior.

How it is used
Adapts pretrained language models to specific tasks, conversational styles, and preferences after general pretraining.
How deep it goes
Explains the supervised loss objective and walks through data formatting, trainer configuration, training, and comparison with a base model.
Examples
Uses Alpaca instruction prompts, ProsocialDialog conversations, and OPUS-100 English–Spanish translation pairs.
What you can do after
Apply fine-tuning via TRL’s SFTTrainer, prepare supervised examples, and compare adapted model outputs with a baseline.

Read how Transformers in Action explains fine-tuning →

Fight Fraud with Machine Learning

Fine-tuning is adapting a pretrained machine-learning model by training it further on task-specific data.

How it is used
Adapts a pretrained GPT model to answer conversational prompts using labeled question-and-answer data.
How deep it goes
Explains the supervised data format and its contrast with pretraining, then defers further improvement to reinforcement learning.
Examples
Uses manually labeled question-and-answer pairs and a diagram contrasting unsupervised text data with supervised pairs.
What you can do after
Evaluate/understand why labeled answers make a pretrained GPT respond to prompts instead of only continuing text.

Read how Fight Fraud with Machine Learning explains fine-tuning →

Hugging Face in Action

Fine-tuning is the adaptation of a pretrained model by continuing training on data for a particular task or domain.

How it is used
Adapts pretrained models for specialized tasks such as sentiment analysis, object detection, classification, and language generation.
How deep it goes
Explains dataset preparation, model and device setup, training configuration, evaluation, saving, and inference without deriving optimization mathematics.
Examples
Uses yelp_polarity reviews, DistilBERT sequence classification, training logs, saved checkpoints, and positive or negative review predictions.
What you can do after
Apply it via Hugging Face Trainer to train, evaluate, save, reload, and use a task-specific classification model.

Read how Hugging Face in Action explains fine-tuning →

The AI Pocket Book

Additional training applied to an existing model to adapt or improve its behavior using new examples.

How it is used
Positions fine-tuning as a late-stage customization choice after prompt improvements, especially for specialized outputs or smaller self-hosted models.
How deep it goes
Explains parameter adjustment, continued training, dataset size, overfitting, and validation, but defers detailed prevention techniques.
Examples
Uses intended-style documents, manually written prompt-output examples, and smaller self-hosted models as concrete cases.
What you can do after
Evaluate and select a fine-tuning strategy using validation data, test data, and checks for overfitting.

Read how The AI Pocket Book explains fine-tuning →

Build AI Drug Discovery Pipelines

Fine-tuning is the continued training of a pretrained model on task-specific data, usually with its parameters initialized from pretraining.

How it is used
Applies pretrained protein representations to antibody classification with limited task-specific training.
How deep it goes
Defines the transfer-learning strategy and model components, but defers fine-tuning implementation details.
Examples
Uses ESM-2, labeled HIV-1 and SARS-CoV-2 antibody sequences, and classification metrics as its concrete examples.
What you can do after
Evaluate/understand how pretrained protein knowledge can be adapted for antibody classification.

Read how Build AI Drug Discovery Pipelines explains fine-tuning →

Machines that Think

Fine-tuning is the continued adjustment of a pretrained model on narrower data or objectives for a particular task or behavior.

How it is used
Uses continued training to specialize pretrained models and reinforce desired or fairer behavior.
How deep it goes
Contrasts full and partial parameter adaptation and explains their risks, without a training procedure or implementation.
Examples
Uses curated examples of refusals, safer redirection, tone, and response formats to illustrate supervised fine-tuning.
What you can do after
Evaluate fine-tuning by distinguishing learned behavioral tendencies from guarantees and weighing specialization against forgetting.

Read how Machines that Think explains fine-tuning →

Microsoft Azure in Action

Fine-tuning is the process of further training a pretrained model on task-specific data to adapt its behavior or vocabulary.

How it is used
Adapts a general-purpose model to specialist review vocabulary when off-the-shelf recommendations fall short.
How deep it goes
Walks through data preparation, wizard submission, job inspection, and deployment; defers real-world production monitoring.
Examples
Uses a JSONL file pairing customer reviews with desired book recommendations for a recommendation engine.
What you can do after
Apply it via Azure AI Foundry’s Fine-Tuning wizard to submit labeled data, inspect a job, and deploy an inference endpoint.

Read how Microsoft Azure in Action explains fine-tuning →

Build Applications with Local AI Models on a Mac

Fine-tuning is the process of further training a pretrained model on selected examples to adapt its behavior or capabilities.

How it is used
Uses fine-tuning to adapt a pretrained chatbot model’s behavior or domain knowledge when prompts or retrieval may not be enough.
How deep it goes
Outlines data preparation, training, export, deployment, and iteration without detailing training internals.
Examples
Uses support-ticket summaries and beginner-friendly explanations as input-output training pairs.
What you can do after
Apply fine-tuning via Unsloth, export to GGUF, and deploy a custom model locally with Ollama.

Read how Build Applications with Local AI Models on a Mac explains fine-tuning →

Applied Reinforcement Learning

Further training of a pretrained model on data or objectives suited to a particular task or use.

How it is used
Aligns a general-purpose language model’s signal with a task-specific schema for portfolio management.
How deep it goes
Explains training on thousands of schema examples and reports measured results, but gives no training procedure.
Examples
Uses a portfolio signal schema, oracle agreement, and comparisons between fine-tuned, base, and naive signals.
What you can do after
Evaluate whether task-specific tuning improves signal agreement and downstream portfolio performance.

Read how Applied Reinforcement Learning explains fine-tuning →

AI Agents and Applications

Fine-tuning is the additional training of a pretrained model on a narrower or task-specific dataset to adapt its behavior.

How it is used
Adapts pretrained language models for specialized tasks, domains, terminology, workflows, and response behavior.
How deep it goes
Defines curated training and major tradeoffs, but stops short of dataset schemas, training code, and evaluation procedures.
Examples
Uses BioMistral, LexiGPT, BloombergGPT, Code Llama, and Claude Code as specialized-model examples.
What you can do after
Apply it via a fine-tuning API or open-source toolkit to adapt a model for specialized behavior.

Read how AI Agents and Applications explains fine-tuning →

Machine Learning System Design

The process of continuing training on an existing model to adapt its parameters to new data or a related task.

How it is used
Uses pretrained models as a deep-learning baseline for adapting existing capabilities to related tasks.
How deep it goes
Explains when to choose fine-tuning and what to compare, but does not detail optimization steps or parameter-freezing mechanics.
Examples
Uses ImageNet pet-breed recognition and PhotoStock CLIP relevancy scoring as concrete adaptation examples.
What you can do after
Apply it by adapting a pretrained model or its components and evaluating the result against simpler baseline options.

Read how Machine Learning System Design explains fine-tuning →

The Complete Obsolete Guide to Generative AI

Fine-tuning is continued training of a pretrained model on task- or domain-specific data to specialize its behavior.

How it is used
Specializes pretrained language models when general off-the-shelf behavior does not suit a task or domain.
How deep it goes
Outlines datasets, architecture adaptation, gradient optimization, and iterative training, but defers practical dataset construction and execution.
Examples
Uses positive-versus-negative sentiment labels and legal or medical domain datasets as specialization examples.
What you can do after
Evaluate/understand when fine-tuning may specialize a model and why it requires proprietary data and substantial hardware.

Read how The Complete Obsolete Guide to Generative AI explains fine-tuning →

Causal AI

Fine-tuning is the process of adapting a pretrained model by continuing parameter training on task-specific or domain-specific data.

How it is used
Aligns pretrained language models with node-specific causal Markov kernels for generating intervention-relevant text.
How deep it goes
Explains model selection, tokenization, dataset splitting, training configuration, generation, and Pyro integration, but not parameter-update mathematics.
Examples
Uses GPT-2 for King actions and BART models for Prince actions, Kingdom fate, and Prince-to-King inference.
What you can do after
Builds task-specific causal text generators with Hugging Face Transformers, then samples and scores their outputs inside Pyro.

Read how Causal AI explains fine-tuning →

Knowledge Graphs and LLMs in Action

Fine-tuning is adapting a pretrained model by continuing its training on targeted data or objectives.

How it is used
Improves domain-specific extraction, schema understanding, and query generation when prompting alone is insufficient.
How deep it goes
Explains dataset preparation, annotation reuse, trade-offs, and selective component replacement without detailing optimization internals.
Examples
Uses entity-relation extraction, schema-aware agents, and knowledge-graph query planning as application examples.
What you can do after
Build task-specific LLM components for more stable extraction or more efficient graph-aware querying.

Read how Knowledge Graphs and LLMs in Action explains fine-tuning →

AI Agents in Action

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

How it is used
Refines training toward a particular use case or domain, informing model selection for domain-specific agents.
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.

Read how AI Agents in Action explains fine-tuning →

Machine Learning Algorithms in Depth

Fine-tuning is adapting a pretrained model to a target task by continuing training, typically with task-specific output parameters.

How it is used
Adapts pretrained transformer models to language-processing tasks such as question answering and language inference.
How deep it goes
Defines task adaptation through an additional output layer but stops short of training mechanics, optimization, or implementation details.
Examples
Uses BERT-based question answering and language inference as concrete fine-tuning applications.
What you can do after
Apply pretrained BERT with an added output layer to multiple language-processing tasks.

Read how Machine Learning Algorithms in Depth explains fine-tuning →

Data Without Labels

Fine-tuning is the adaptation of a pretrained model's parameters to optimize performance on a target task.

How it is used
Adapts a pretrained DBN to supervised classification or regression after unsupervised representation learning.
How deep it goes
Explains layer-wise pretraining, joint weight adjustment, objectives, benefits, and training difficulties without detailing optimizer implementation.
Examples
Uses DBNs for speech recognition, image recognition, dimensionality reduction, feature learning, and classification.
What you can do after
Apply supervised fine-tuning to adjust a pretrained DBN for classification or regression using labeled data.

Read how Data Without Labels explains fine-tuning →

Machine Learning Platform Engineering

Fine-tuning is the additional training of a pretrained model on task-specific data to adapt its behavior to a new task or domain.

How it is used
Applies pretrained models to domain-specific production tasks such as identity-card detection.
How deep it goes
Defines adaptation and dataset splits, then connects training with evaluation and retraining without detailing optimization internals.
Examples
Uses YOLOv8, COCO, identity cards, passports, and separate training, testing, and validation images.
What you can do after
Apply it via YOLOv8 to train a custom detector for objects absent from its original classes.

Read how Machine Learning Platform Engineering explains fine-tuning →

Outlier Detection in Python

Fine-tuning is the continued training of a pretrained model, usually on a new task or domain, by adjusting some or all of its parameters.

How it is used
Applies pretrained neural networks to related tasks with less retraining than training a model from scratch.
How deep it goes
Explains reused embeddings, selective layer retraining, benefits, and weaker transferability for tabular data.
Examples
Uses cat-versus-dog classification adapted to distinguishing different types of dogs.
What you can do after
Apply it via a pretrained neural network by retraining a final layer or adding a task-specific layer.

Read how Outlier Detection in Python explains fine-tuning →

Build an Advanced RAG Application (From Scratch)

Fine-tuning is the adaptation of an already trained model by continuing parameter optimization on data for a specific task or domain.

How it is used
Positions fine-tuning as the application-specific adaptation stage for language models and LLM-powered systems.
How deep it goes
Explains pre-training, parameter adjustment, and compute demands, but stops short of implementation procedures or hyperparameter guidance.
Examples
Names chatbots, text summarization, content generation, sentiment analysis, and RAG as application contexts for model adaptation.

Read how Build an Advanced RAG Application (From Scratch) explains fine-tuning →

AI Governance

Fine-tuning is the additional training of a pretrained model on task-specific or organization-specific data to adapt its behavior or capabilities.

How it is used
Adapts pretrained models to specific domains using tailored data.
How deep it goes
Connects fine-tuning to safety degradation and poisoning risks, but does not detail training procedures.
Examples
Cites adversarial examples against GPT-3.5 Turbo and benign medical, financial, and legal datasets used with Llama-2 variants.
What you can do after
Operate/configure it with validated, cleaned data and safety retesting after fine-tuning.

Read how AI Governance explains fine-tuning →

Financial AI in Practice

Fine-tuning adapts a pretrained model by continuing training on task-specific or domain-specific data.

How it is used
Adapts a pretrained model’s behavior, such as writing in a financial platform’s distinctive style.
How deep it goes
Explains the goal, data curation, PEFT trade-offs, and a conceptual LoRA recipe, but not a complete training workflow.
Examples
Uses 200 analyst-written input-output examples to adapt summaries of AlphaStream community posts.
What you can do after
Apply it via Hugging Face Transformers and PEFT to customize a pretrained model with LoRA.

Read how Financial AI in Practice explains fine-tuning →

Also covered in

What to know first

Related concepts

Questions about fine-tuning

What is fine-tuning?

Fine-tuning is the continued training of a pretrained model on targeted data or objectives to adapt its parameters or behavior to a task, domain, or use.

Which Manning books explain fine-tuning?

Building Specialized AI Systems, LLMs in Production, Natural Language Processing in Action, Second Edition, Generative AI in Action, Software Testing with Generative AI, The Art of AI Product Development, Reinforcement Learning from Human Feedback, Deep Learning with R, Third Edition and 44 more.

What should I know before learning fine-tuning?

Manning books that teach fine-tuning usually introduce language model, foundation model, parameter and GPT model first.

What is the difference between fine-tuning and retrieval-augmented generation?

Fine-tuning is the continued training of a pretrained model on targeted data or objectives to adapt its parameters or behavior to a task, domain, or use. Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.

What is fine-tuning also called?

Fine-tuning is also called fine-tune or finetuning.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.