Recently, the SF10 group of the Institute of Physics of the Chinese Academy of Sciences/Beijing National Research Center for Condensed Matter Physics and the Computer Network Information Center of the Chinese Academy of Sciences have jointly applied AI large models to the field of materials science, as reported by the Shanghai Securities Daily on November 3. The collaborative team fed tens of thousands of chemical synthesis pathway data to the large language model LLAMA2-b, resulting in a MatChat model that can be used to predict the synthesis path of inorganic materials. The model can make logical inferences according to the structure asked, and output the corresponding preparation process and formula. At present, the model has been deployed and is open to all materials researchers