arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.15006cs.CLcs.AI
收藏

Airavata:引入印地语指令微调大语言模型

Airavata: Introducing Hindi Instruction-tuned LLM

Nilekani Centre at AI4Bharat(AI4Bharat的Nilekani中心);IIIT D&M Kancheepuram(坎奇普兰IIIT D&M);Flipkart;University of Surrey(萨里大学);A * STAR(新加坡科技研究局);IIT Madras(马德拉斯印度理工学院);NICT(日本国立信息通信技术研究所);IBM Research(IBM研究院);Microsoft(微软)
Jay Gala, Thanmay Jayakumar, Jaavid Aktar Husain, Aswanth Kumar M, Mohammed Safi Ur Rahman Khan, Diptesh Kanojia, Ratish Puduppully, Mitesh M. Khapra, Raj Dabre… 展开作者

Jay Gala, Thanmay Jayakumar, Jaavid Aktar Husain, Aswanth Kumar M, Mohammed Safi Ur Rahman Khan, Diptesh Kanojia, Ratish Puduppully, Mitesh M. Khapra, Raj Dabre, Rudra Murthy, Anoop Kunchukuttan

AI总结:

本文发布面向印地语的指令微调大语言模型 Airavata,通过微调 OpenHathi 并公开 IndicInstruct 数据集与评估框架,以推动印度语言大模型研究。

摘要:

我们宣布“Airavata”的首次发布,这是一个面向印地语的指令微调大语言模型(LLM)。Airavata 通过使用多样化的印地语指令微调数据集对 OpenHathi 进行微调而创建,使其更适合辅助性任务。随模型一同,我们还分享了 IndicInstruct 数据集,这是一个多样化的指令微调数据集集合,旨在支持面向印度语言大语言模型的进一步研究。此外,我们提供了评估基准和一个用于评估大语言模型在印地语各项任务中表现的框架。目前,Airavata 支持印地语,但我们计划将其扩展到全部 22 种印度官方计划语言。您可以在 https://ai4bharat.github.io/airavata 访问所有相关资源。

英文摘要:

We announce the initial release of "Airavata," an instruction-tuned LLM for Hindi. Airavata was created by fine-tuning OpenHathi with diverse, instruction-tuning Hindi datasets to make it better suited for assistive tasks. Along with the model, we also share the IndicInstruct dataset, which is a collection of diverse instruction-tuning datasets to enable further research for Indic LLMs. Additionally, we present evaluation benchmarks and a framework for assessing LLM performance across tasks in Hindi. Currently, Airavata supports Hindi, but we plan to expand this to all 22 scheduled Indic languages. You can access all artifacts at https://ai4bharat.github.io/airavata.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑