What is Low-Rank Adaptation (LoRA) for Gemma?

Опубликовано 14 января 2025, 20:00

Level up your machine learning skills with Low-Rank Adaptation (LoRA) for fine tuning your AI model. With Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reduces the number of trainable parameters for downstream tasks.

Watch more Generative AI Experiences for Developers → goo.gle/genAI4devs

#GoogleCloud #DevelopersAI

Speaker: Paige Bailey
Products Mentioned: Gemma, Google Colab, Gemini