SEA-LION-v4.8: A Technical Report
Ahmed Mohammad Dabeer, Ahn Jeongmi, Anocha Sutaveephamochanon, Antonyrex Sajeban, Aulia Adila, Chan Hok Teng, Adwin, Cheng Zi Yi, Nicholas Zhuang Ziyi, Choa Hsueh Mei Esther, David Ong Tat-Wee, Evelyn Tan Chor Phin, Heng Cheng Peng, Jonathan, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Leslie Teo Eng Sipp, Liew Rachel, Limkonchotiwat Peerat, Montalan Jann Railey Estrada, Muhammad Ridzuan Bin Mokhtar, Nagarajan Karthik, Ng Boon Cheong, Raymond, Ngui Jian Gang, Nguyen Thanh Ngan, Tasawong Panuthep, Pereira Mark Gregory, Phang Shi Wei Benjamin, Poon Yip Hung, Joseph, Rengarajan Hamsawardhini, Siow Wei Kang Bryan, Tai Ngee Chia, Tan Choon Meng, Tan Le Min, Sheryl, Tan Siao Wei, Tan Yi Xian, Tee Jun Yun, Teng Kok Wai, Tjhi William Chandra, Tuchinda Pume, Wu Donghang, Yong Xianbin, Yosephine, Zhang Zhou
Abstract
We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 30B-A3B and 120B-A12B models, with both continued-pretrained base checkpoints and post-trained variants. We adapt the models using Southeast Asian, reasoning, code, and multilingual parallel datasets, followed by post-training with supervised fine-tuning and online on-policy distillation. On SEA-HELM, the 30B-A3B model improves the overall SEA score from 46.06 to 51.57, while the 120B-A12B model improves from 49.30 to 63.44. The strongest gains are observed in instruction following, natural language reasoning, and natural language understanding across seven Southeast Asian languages.