LoRA
Concept
A technique that allows for tuning only a subset of a large model's weights, making fine-tuning more efficient and memory-friendly.
Mentioned in 2 videos
Save the 2 videos on LoRA to your own pod.
Sign up free to keep building your knowledge base on LoRA as more episodes are added.
Videos Mentioning LoRA
Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 8 - Trending Topics
Stanford Online
A technique that allows for tuning only a subset of a large model's weights, making fine-tuning more efficient and memory-friendly.
Building with Instruction-Tuned LLMs: A Step-by-Step Guide
DeepLearningAI
A parameter-efficient fine-tuning technique that significantly reduces trainable parameters and compute requirements. Applied to the query-key-value module in Bloom Z.