Olive: An Instruction Following LLaMA Model For Odia Language

Abstract

The AI community is experiencing a profound impact from Large Language Models (LLMs), and the introduction of ChatGPT and GPT-4 is prompting a reconsideration of the potential of artificial general intelligence(AGI). However, most of the LLMs are trained in English and other high-resource languages, resulting in the unavailability of LLM and its related technologies and services for many low-resource languages. In India, where only 10% of the population is proficient in English, the need for LLM models adapted to regional languages becomes crucial.In this paper, we emphasized the need for LLM for the low-resource Odia language by evaluating the available LLM-supporting Odia language. We describe the development process of the instruction-tuning LLM model for Odia. The developed instruction tuning Odia LLM is available freely for research and non-commercial purposes.

Ähnliche Arbeiten