large language model

A neural network trained on huge amounts of text that generates text by predicting one token at a time from everything before it.

In more detail

LLM stands for large language model. It reads a prompt as tokens, scores every possible next token, picks one, and repeats until it stops, so its output varies and can be fluent but wrong. Applications reach one through a provider's API or run an open-weight model locally, and wrap it in prompts, retrieval, tools and evals.

Related terms

Taught in

References

Certification courses