@misc{4d725104ace1493eb6b1576532877a8e,
title = "Airavata: Introducing Hindi Instruction-tuned LLM",
abstract = " 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 this https URL. ",
keywords = "Airavata, Hindi-language LLM, IndicInstruct dataset, instruction-tuning, LLM evaluation benchmarks",
author = "Gala, \{Jay P.\} and Thanmay Jayakumar and Husain, \{Jaavid Aktar\} and Aswanth, \{Kumar M.\} and Khan, \{Mohammed Safi Ur Rahman\} and Diptesh Kanojia and Ratish Puduppully and Khapra, \{Mitesh M.\} and Raj Dabre and Murthy, \{V. Rudra\} and Anoop Kunchukuttan",
note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",
year = "2024",
doi = "10.48550/ARXIV.2401.15006",
language = "English",
volume = "abs/2401.15006",
type = "Other",
}