ORCIDGitHubLinkedIn
RSS Curriculum Vitae TR

Fine-Tuning

Turkish equivalent: İnce ayarDomain: Machine Learning

Additional training of a pretrained model on task-specific, domain-specific, or instruction data to adapt its behavior or representation.

Generalisation and Measurement Boundary

Fine-tuning changes model parameters; it should not be used as a substitute for retrieval when the requirement is to access fresh or auditable external facts.

Updated:

Related concepts

Machine Learning

Related technical publications

Publications whose title or summary directly references this concept.

Large Language Models

A comprehensive course note on large language models from language modeling and Transformer architecture through pre-training, post-training, RAG, fine-tuning, reasoning, tool use, agents, security, evaluation, and production engineering, connected to other AI paradigms.