This document outlines a roadmap for learning and working with Large Language Models (LLMs). It includes curated work items, topics to cover, and useful resources.
| Work Item | Topics Covered | Resource Link |
|---|---|---|
| Python | Any tutorials/trainings are good. Should include basic to intermediate skills. | |
| Intro to LLMs | LLMs, LoRA, qLoRA, Prompt Engineering, Fine-tuning, RAG, Embeddings | Course Link |
| How Transformer LLMs Work | How Transformer LLMs Work | |
| LangChain Chat with Your Data | LangChain Chat with Your Data | |
| GenAI Introduction | Specialization Link |
- Start with Python — Comfortable with Python basics, as it’s essential for all LLM-related work.
- Understand LLM Fundamentals — Learn how LLMs work, key architectures like Transformers, and techniques like LoRA/qLoRA.
- Explore Tools and Frameworks — Gain experience with LangChain, RAG (Retrieval-Augmented Generation), and prompt engineering.
- Take Online Courses — Follow the linked resources to solidify your understanding and skills.