BriefGPT.xyz
Feb, 2024
Aya模型:一种指令微调的开放式多语言语言模型
Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model
HTML
PDF
Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, Wei-Yin Ko, Daniel D'souza...
TL;DR
用101种语言的指令追踪的Aya广泛多语言生成语言模型在多任务中表现优越,同时扩展了用于99种语言的多语言评估的最新技术水平,并进行了关于优化微调混合成分、数据修剪以及模型的毒性、偏见和安全性的详细研究。
Abstract
Recent breakthroughs in
large language models
(LLMs) have centered around a handful of data-rich languages. What does it take to broaden access to breakthroughs beyond first-class citizen languages? Our work introduces
→