Large Language Models

A Large language model is a large language model, commonly based on a transformer, that processes a sequence of token units within a context window.

Japanese terms

1. Large language model — 大規模言語だいきぼげんごモデル: A language model with many parameters trained on large text collections for broad language capabilities.
2. Language model — 言語げんごモデル: A model that assigns probabilities to sequences of language elements or predicts language content.
3. Transformer — トランスフォーマー: A neural-network architecture that processes relationships between tokens primarily through attention mechanisms.
4. Token — トークン: A unit of text or other input that a model processes as one element of a sequence.
5. Context window — コンテキストウィンドウ: The amount of input and generated content a model can consider in one interaction.

Related topics

Retrieval-augmented generation supplies external knowledge to an LLM, while AI agents use models to plan and act.