TensorX
返回文献探索

Paper · arXiv 2408.17024

InkubaLM: A small language model for low-resource African languages

Atnafu Lambebo Tonja, Bonaventure F. P. Dossou, Jessica Ojo, Jenalea Rajab, Fadel Thior, Eric Peter Wairagala, Aremu Anuoluwapo, Pelonomi Moiloa, Jade Abbott, Vukosi Marivate, Benjamin Rosman

14 upvotesAugust 30, 2024arXiv 预印本
AI 摘要

InkubaLM, a small language model with 0.4 billion parameters, outperforms larger models in various tasks including sentiment analysis and demonstrates remarkable consistency across multiple languages, challenging the necessity for substantial resources in effective language models.

Abstract

High-resource language models often fall short in the African context, where there is a critical need for models that are efficient, accessible, and locally relevant, even amidst significant computing and data constraints. This paper introduces InkubaLM, a small language model with 0.4 billion parameters, which achieves performance comparable to models with significantly larger parameter counts and more extensive training data on tasks such as machine translation, question-answering, AfriMMLU, and the AfriXnli task. Notably, InkubaLM outperforms many larger models in sentiment analysis and demonstrates remarkable consistency across multiple languages. This work represents a pivotal advancement in challenging the conventional paradigm that effective language models must rely on substantial resources. Our model and datasets are publicly available \url{https://huggingface.co/lelapa} to encourage research and development on low-resource languages.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号