Foundational model

As explained in LLMs in Production

A foundation model is a broadly pretrained model that can be adapted to multiple downstream tasks or domains.

Need an LLM for a specific task? You usually do not need to train one from scratch. A foundation model supplies pretrained weights that you can adapt; choosing the right starting model can make or break the project. section 4.0 section 4.1

A foundation model starts as an untrained model trained on a large, general-purpose corpus. That pretraining gives it broad language patterns rather than expertise in one task. Finetuning then updates it on a smaller, curated dataset for a task or domain; prompting can further steer the form of its responses. section 5.2 section 5.2.2

Figure 5.1 The training life cycle of an LLM. We start by creating a foundation model based on a large corpus of text, which we later finetune using a curated dataset for a specific task. We can then further improve the model by using the model itself and techniques like prompting to enhance or enlarge our curated dataset.

The life-cycle diagram places the foundation model between broad pretraining and task-specific finetuning, with prompting as a later step. section 5.2

Treat the starting model as a practical choice, not just a benchmark winner:

• Check how it was trained and what data it saw; that history helps determine whether it suits your task. section 4.1
• Prepare training data, a tokenizer or other text encoder, and evaluation data alongside the model. section 4.0
• Budget for the route you choose. Initial pretraining demands substantial computation; finetuning generally uses a smaller dataset and fewer resources. section 5.2 section 5.2.2

From broad language to a specific task

A model pretrained on sources such as Wikipedia, books, or internet text can be updated with task-specific data for sentiment analysis, text classification, or question answering. The broad training supplies a starting point; the smaller update directs it toward the job. section 5.2.2

How LLMs in Production covers it

How deep it goes

Explains broad pretraining and subsequent finetuning, but does not detail foundation-model architecture.

Examples

Uses Wikipedia, books, and internet text as pretraining sources, then sentiment analysis, text classification, and question answering as target tasks.

What it assumes

Builds from the basic LLM training life cycle and explains how pretraining leads into transfer learning.

What you can do after

Evaluate/understand whether a pretrained model is a suitable starting point before preparing data for finetuning.

How it connects

Links foundation models to transfer learning, finetuning, prompting, tokenizers, and evaluation data.

liveBookmanning.com

Read LLMs in Production on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA model whose parameters were fitted on a source task or dataset before reuse.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA model trained beforehand on large-scale data and then reused for downstream tasks or analysis without starting from scratch.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA foundation model is a large pretrained model intended to support many downstream tasks with little or no task-specific retraining.
• 

  liveBookmanning.com
  AI-Powered SearchA pretrained model is a model that has already been trained on general data before adaptation to a particular task or domain.
• 

  liveBookmanning.com
  Generative AI in ActionA pretrained model is a machine-learning model that has already been trained on an initial dataset before being adapted to another task or dataset.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsA foundation model is a machine learning model trained on large, diverse data and applicable to a wide variety of tasks, often through adaptation or fine-tuning.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA neural network already trained on prior data and reused for inference or further training.
• 

  liveBookmanning.com
  Machine Learning System DesignA machine learning model whose parameters were learned previously on a dataset or task before being applied or adapted to another task.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentA foundation model is a broadly trained machine learning model that can be adapted to support multiple downstream tasks.
• 

  liveBookmanning.com
  How Large Language Models WorkA foundation model is a broadly trained model that can be adapted or used as a basis for many applications.
• 

  liveBookmanning.com
  Hugging Face in ActionA pretrained model is a machine learning model whose parameters have already been learned from a training dataset before being adapted or used for a particular task.
• 

  liveBookmanning.com
  Effective Data AnalysisA foundation model is a broadly pretrained model that can be adapted or prompted for many downstream tasks and domains.
• 

  liveBookmanning.com
  The AI Pocket BookA preexisting model used as-is or with minimal adaptation instead of building one from scratch.
• 

  liveBookmanning.com
  Reinforcement Learning from Human FeedbackA foundation model is a broadly pretrained model that can be adapted to support multiple downstream tasks.
• 

  liveBookmanning.com
  Software Testing with Generative AIA foundational model is a pretrained machine-learning model that provides a general base for further adaptation or specialization.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA pretrained model is a model whose parameters were previously learned from a separate training corpus or task.
• 

  liveBookmanning.com
  Transformers in ActionA pretrained model is a machine-learning model whose parameters have already been learned from a broad training corpus before adaptation to a specific task.
• 

  liveBookmanning.com
  Deep Learning with JAXA model that has already been trained on a large corpus and can be reused directly or adapted to a new task.
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentA foundational model is a broadly trained model that can be adapted to support many downstream tasks and applications.
• 

  liveBookmanning.com
  Financial AI in PracticeA foundation model is a large, broadly trained model that can be adapted or guided for many downstream tasks.

Compare how 21 books explain foundational model →

Related concepts

• language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• pretrained modelkind of · A pretrained model is a machine-learning model whose parameters were learned through prior training before it is used or adapted for a subsequent task.
• instruct modelincludes · An instruction-tuned model is a pretrained model further trained to follow natural-language instructions and produce task-appropriate responses.
• feature engineeringused by · Feature engineering is the creation, transformation, or selection of input features from data to provide useful representations for analysis or modeling.
• TimesFMincludes · TimesFM is a foundation model designed for deterministic time-series forecasting.

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