Large Language Models for Software Engineering
The lab materials for a university course on large language models for software engineering, covering transformer foundations and their application to prompt engineering, RAG and code-review tasks.
This repository holds the lab materials for Large Language Models for Software Engineering, a course at Politecnico di Torino. The first part covers foundations of large language models: deep learning with PyTorch, using transformer models such as T5 through the HuggingFace suite, analyzing encoder-only models like BERT and decoder-only models like GPT, causal language modeling, and efficient fine-tuning and inference.
The second part applies these foundations to software engineering tasks: prompt engineering and retrieval-augmented generation with Llama, building user-story and chain-of-thought architectures, and evaluating router agents with ROC analysis. It is distributed as Jupyter notebooks.