Episode Details
Back to Episodes
【第47期】LoRA vs Full Fine-tuning
Published 1 year, 7 months ago
Description
Seventy3: 用NotebookLM将论文生成播客，让大家跟着AI一起进步。
今天的主题是：
LoRA vs Full Fine-tuning: An Illusion of Equivalence
Summary
This research paper investigates the differences between two popular methods for fine-tuning large language models: full fine-tuning and Low-Rank Adaptation (LoRA). While both approaches can achieve comparable performance on downstream tasks, the authors show that these methods learn fund...去小宇宙查看完整单集简介
前往小宇宙评论区与主播互动
今天的主题是：
LoRA vs Full Fine-tuning: An Illusion of Equivalence
Summary
This research paper investigates the differences between two popular methods for fine-tuning large language models: full fine-tuning and Low-Rank Adaptation (LoRA). While both approaches can achieve comparable performance on downstream tasks, the authors show that these methods learn fund...去小宇宙查看完整单集简介
前往小宇宙评论区与主播互动