Low-resource languages such as Sinhala are often overlooked by open-source Large Language Models (LLMs). In this research, we extend an existing multilingual LLM (Llama-3-8B) to better serve Sinhala. We enhance the LLM tokenizer with Sinhala specific vocabulary and perform continual pre-training on a cleaned 10 million Sinhala corpus, resulting in the SinLlama model. This is the very first decoder-based open-source LLM with explicit Sinhala support. When SinLlama was instruction fine-tuned for three text classification tasks, it outperformed base and instruct variants of Llama-3-8B by a significant margin.
@article{arxiv.2508.09115,
title = {SinLlama -- A Large Language Model for Sinhala},
author = {H. W. K. Aravinda and Rashad Sirajudeen and Samith Karunathilake and Nisansa de Silva and Surangika Ranathunga and Rishemjit Kaur},
journal= {arXiv preprint arXiv:2508.09115},
year = {2025}
}