MilChat: A Large Language Model and Application for Military Equipment

To offer the military personnel a good service of assisting them to get information about enemy's equipment outside Internet, we build a system named MilChat which includes a large language model that has the ability to generate texts and an application which is easy to use. The model of MilChat is fine-tuned by the method of LoRA with military datasets from the basic model, Qwen-7B-Chat which is opensource and has good performance. After fine-tuning, the new model has higher scores than the basic one. Besides, we use the method of Prompt Learning to limit the answers into a standard format. Therefore, it is more accurate and professional than the basic model. This study has also a value of industrial application.