@inproceedings{aravinda2025sinllama,
  title={{SinLlama-A Large Language Model for Sinhala}},
  author={Aravinda, H W K and Sirajudeen, Rashad and Karunathilake, Samith and de Silva, Nisansa and Ranathunga, Surangika and Kaur, Rishemjit},
   booktitle={Moratuwa Engineering Research Conference (MERCon)},
  year={2025},
  abstract={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.},
doi={10.1109/MERCon67903.2025.11217094},
  url={https://arxiv.org/pdf/2508.09115},
misc={https://arxiv.org/pdf/2508.09115,SIN:NLP:ML,https://goo.gl/iY6aTr}
}