← Back

LoRA adapters

technique 1 mention from 1 sources

Low-Rank Adaptation technique for efficiently fine-tuning large language models by updating smaller weight matrices instead of the full model.

ai ml fine tuning
1

sources

Mentioned by

Sebastian Raschka

All mentions

Sebastian Raschka mentioned ✓ High confidence
"One thing people still use is LoRA adapters. These are basically, instead of updating the whole weight matrix, there are two smaller weight matrices"
From: State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490 • ▶ 2:43:31 • Jan 2026

Attribution: Sebastian explains LoRA adapters as a technique people use for model customization