Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

foundation model

A large pretrained model general enough to be adapted to many downstream tasks rather than built for just one.

A foundation model is a model pretrained on broad data at scale that serves as the starting point for many downstream applications, via prompting, fine-tuning, or further adaptation, rather than being trained from scratch for each task.

Examples

  • GPT-4 and Llama serve as foundation models: pretrained once, then adapted via prompting or fine-tuning into chatbots, coding assistants, and summarizers.

See also

large language model (LLM) pretraining base model
Read the full section →
Graph settings

Calculator