Large Language Models: Theory and Practice

This course provides an in-depth exploration of designing and implementing large language models (LLMs) from scratch. Students will gain a strong theoretical foundation in deep learning architectures, pre-training and fine-tuning strategies, and optimization techniques for scaling LLMs. The course emphasizes hands-on experience, guiding students through implementing transformers, training models on realworld datasets, and deploying efficient inference pipelines.

Credits

3 credits

Course Code

EE 768