BriefGPT.xyz
Aug, 2024
通过对比微调改进小型语言模型的文本嵌入
Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning
HTML
PDF
Trapoom Ukarapol, Zhicheng Lee, Amy Xin
TL;DR
本研究解决了小型语言模型在性能和可访问性方面的不足，提出了一种通过对比微调改善文本嵌入的方法。研究结果表明，该方法显著提高了MiniCPM等模型的性能，MiniCPM的平均性能提升达56.33%。
Abstract
While Large
Language Models
show remarkable performance in
Natural Language Understanding
, their resource-intensive nature makes them less accessible. In contrast, smaller
→