This project focuses on developing artificial intelligence (AI) tools to help legal professionals manage and understand large legal documents efficiently. Our main goal is to train and evaluate large language models that are specifically designed for legal texts. We plan to use large language models such as RoBERTa, BERT transformers, and the open source Llama3 model. These models need substantial computational resources for training and evaluation, which our current infrastructure cannot support. Thus, we require access to a supercomputing cluster to handle these tasks efficiently.