This module introduces foundational concepts and practical workflows for working with Large Language Models (LLMs). Topics include terminology (e.g., ChatGPT vs. LLM, inference phases, training stages, and model compression techniques), the LLM ecosystem (vector databases, inference APIs, and fine-tuning libraries), and the model lifecycle. Participants will build a simple LLM-based system from scratch, starting with “Hello World” inference using Hugging Face, and deploy an LLM API using Modal for serverless deployment.
Building a Shakespearean Language Model
Building an n-gram language model
Building self-attention
Building the feed-forward neural network
Assembling the transformer-based language model
Evaluating and deploying a transformer-based language model
Datasets
Low-Rank Adapters for Instruction Tuning
Retrieval-Augmented Generation (RAG)
The Future of Large Language Models
Machine learning operations
Agents
Use huggingface’s peft on an actual pre-trained model, like Llama