Introducing cosmosGPT: Monolingual Training for Turkish Language Models

Abstract: The number of open source LLMs that can produce Turkish is increasing day by day, as in other languages. In order to create the basic versions of such models, the training of multilingual models is usually continued with Turkish corpora. The alternative is to train the model with only Turkish corpora. In this study, we first introduce the cosmosGPT models that we created with this alternative method. Then, we introduce new finetune datasets for basic LLMs to fulfill user requests and new evaluation datasets for measuring the capabilities of Turkish LLMs. Finally, a comprehensive comparison of the adapted Turkish LLMs on different capabilities is presented. The results show that the LLMs we built with the monolingual corpus have promising performance despite being about 10 times smaller than the others.