This repository contains detailed code examples for the course Generative AI With Large Language Models, offered by DeepLearning.AI on Coursera.

The repository contains 4 folders:

• code - Contains two coding assignments:
  • Fine-Tuning Lab.ipynb - Assignment which covers Instruction Fine-Tuning using LoRA.
  • RLHF Lab.ipynb - Assignment which covers using Reinforcement Learning From Human Feedback to align LLMs.
• Week 1:
  • Transformers - Basics of Transformers.
  • Prompting and Prompt Engineering - Basics of prompting, prompt engineering and inference configuration parameters (temperature, etc).
  • Pre-training Large Language Models - Basics of how LLMs are pre-trained.
  • Efficient Multi-GPU Compute Strategies - Approaches available for training LLMs in a distributed manner.
• Week 2:
  • Instruction Fine-Tuning - Basics of fine-tuning LLMs.
  • Model Evaluation - Metrics and Benchmarks - Details on evaluation metrics and benchmarks for LLMs.
  • Parameter Efficient Fine Tuning (PEFT) - Basics of PEFT, covering LoRA and Soft Prompts.
• Week 3:
  • Reinforcement Learning From Human Feedback (RLHF) - Basics of RLHF.
• markdown - Contains the same files as above except in Markdown format for those who prefer to read directly on GitHub.