Paper · arXiv 2412.19638
Xmodel-2 Technical Report
Wang Qun, Liu Yang, Lin Qingquan, Qu Zhijiu, Jiang Ling
Xmodel-2, a 1.2-billion-parameter large language model, utilizes a unified set of hyperparameters across different scales and the WSD learning rate scheduler to achieve state-of-the-art performance in complex reasoning tasks with efficient training.
Abstract
Xmodel-2 is a 1.2-billion-parameter large language model designed specifically for reasoning tasks. Its architecture enables different model scales to share a unified set of hyperparameters, allowing for extensive experimentation on smaller models and seamless transfer of optimal configurations to larger models. To maximize training efficiency and stability, Xmodel-2 employs the WSD learning rate scheduler from MiniCPM. Pretrained on 1.5 trillion tokens from diverse sources, Xmodel-2 achieves state-of-the-art performance in complex reasoning and agent-based tasks, while maintaining low training costs. These results highlight the potential of efficient model design and training strategies in advancing reasoning capabilities. Model checkpoints and code are publicly available on GitHub at https://github.com/XiaoduoAILab/Xmodel-2