Encyclopedia · 176 concepts

NLP & Language · advanced · concept 95 of 176

Fine-Tuning LLMs

Adapting a pretrained LLM to a specific task or domain by training on additional data. LoRA and QLoRA enable efficient fine-tuning by only updating a small fraction of parameters.

Key terms

LoRAQLoRAPEFTInstruction tuningAdapter layers

Guides and articles

Courses, papers, and more