# SEA-LION

A family of open-source large language models tuned to better understand Southeast Asia's diverse languages and cultures, developed by AI Singapore's Products Pillar.

SEA-LION, short for Southeast Asian Languages in One Network, targets under-represented population groups and low-resource languages in the Southeast Asian region. Its releases span from small pre-trained-from-scratch models to large continued-pretrained and supervised-fine-tuned models built on bases such as Llama, Gemma, Qwen and NVIDIA Nemotron, up to a 120-billion-parameter mixture-of-experts model with 128K context.

Models are distributed in base, instruct, vision-language, reasoning and GGUF-quantized variants, along with a separate SEA-LION embedding model. The project's site documents how to access the models, hosting options and how-to guides for the SEA-LION family.

Website: https://sea-lion.ai