The investigation and development of chatbot related to NBA players

Abstract

At present, the utilization and development of large language models have been relatively mature, but there are still some areas that have not yet been involved, nba player information retrieval is one of them, this paper will be on through the development and design of large language models, so that it becomes a chatbot to facilitate user retrieval. This project uses mata's llama2-13b model to act as a chatbot, the model can play a great performance in the case of minimizing the memory, and can well meet the user's needs, by imitating the database of the big language model to build a database on nba player information, so that the nba player information is filled into the model for the model to learn, and through the model itself to continuously learn and Through the model's own continuous learning and imitation of human language, the model can be made to output as concise a language as possible to describe the personal information of the nba players, and then meet the user's needs. In this project, the model successfully reads the database and outputs the information that the user wants to get in easy-to-understand language, so that the user can get the personal information of the NBA players more conveniently and intuitively, and the correctness rate reaches the expectation, which makes the study successful.