Glossary Library

Technical GlossaryGenerative AI and LLM

Model Checkpoint

A saved model state captured at a certain stage of training and reusable later.

The concept of a checkpoint is important not only for safety in large-scale model development, but also for iterative experimentation and deployment management. Intermediate versions can be used for benchmarking, error analysis, rollback, and branching into different fine-tuning paths. It provides operational control across the foundation model lifecycle.

You Might Also Like

Explore these concepts to continue your artificial intelligence journey.

Glossary Cover

yapay-zeka-temelleri

Self-Supervised Learning

An approach that enables strong representation learning by generating supervision signals from the internal structure of the data itself.

Glossary Cover

bilgisayarli-goru

Promptable Segmentation

A flexible visual separation approach that performs segmentation guided by prompts such as points, boxes, or text.

Glossary Cover

uretken-yapay-zeka-ve-llm

Generative Model

A family of models that can generate new samples rather than only predicting labels.