LLMs for Engineers

CHEG 667-013 — Chemical Engineering with Computers
Department of Chemical and Biomolecular Engineering, University of Delaware

A hands-on workshop on Large Language Models and machine learning for engineers. Learn how to train a GPT from scratch, run local models, build retrieval-augmented generation systems, then tie it back to underlying machine learning methods by implementing a simple neural network.

Sections

#	Topic	Description
01	nanoGPT	Train a small transformer on Shakespeare. Explore model parameters, temperature, and text generation.
02	Local models with Ollama	Run pre-trained LLMs locally. Summarize documents, query arXiv, generate code, build custom models.
03	Retrieval-Augmented Generation	Build a RAG system: chunk documents, embed them, and query with an LLM grounded in your own data.
04	Advanced retrieval	Hybrid BM25 + vector search with cross-encoder re-ranking. Compares summarization versus raw retrieval.
05	Building a neural network	Implement a one-hidden-layer network from scratch in numpy, then in PyTorch. Fits C_p(T) data for N₂.

Prerequisites

• A terminal (macOS/Linux, or WSL on Windows)
• Python 3.10+
• Basic comfort with the command line
• Ollama (sections 02–04)

Getting started

Clone this repository and work through each section in order:

git clone https://lem.che.udel.edu/git/furst/llm-workshop.git
cd llm-workshop

Each section has its own README.md with a full walkthrough, exercises, and any code or data needed.

Python environment

Install uv (a fast Python package manager), then:

uv sync

This creates a .venv/ virtual environment and installs all dependencies from the lock file. To run scripts:

uv run python 05-neural-networks/nn_torch.py

Or activate the environment directly:

source .venv/bin/activate
python 05-neural-networks/nn_torch.py

License

MIT

Author

Eric M. Furst, University of Delaware