Era of Generative AI

Welcome to the Era of Generative AI! 🚀

This repository introduces Generative Artificial Intelligence (AI), where machines create lifelike images, human-like text, and more. Explore three core parts for deeper insights.

Table of Contents

1. About This Repository
2. What to Expect
3. Part 1: Foundations of Generative AI
4. Part 2: Large Language Models (LLMs)
5. Part 3: Advanced Concepts and Applications
6. Contribution Guidelines
7. References
8. Reading Materials

About This Repository

A comprehensive guide to Generative AI, covering models, architectures, and applications with code, tutorials, and research.

What to Expect

• Code Samples: Practical implementations (code/).
• Tutorials: Step-by-step guides (tutorials/).
• Research: Key paper summaries (papers/).

Part 1: Foundations of Generative AI

Learn the basics:

• Generative Adversarial Networks (GANs): Generator vs. discriminator (code/generative_models/gans/).
• Variational Autoencoders (VAEs): Latent space sampling (code/generative_models/vaes/).
• Diffusion Models: Iterative denoising (code/generative_models/diffusion/).

Details: part1_foundations.md

Part 2: Large Language Models (LLMs)

Explore LLMs and Transformers:

• Key Models: GPT-3/4, BERT, T5 (code/llms/).
• Transformer Architecture: Attention, positional encoding (papers/attention_is_all_you_need.md).

Details: part2_llms.md

Part 3: Advanced Concepts and Applications

Discover advanced topics:

• Retrieval-Augmented Generation (RAG): Enhance generation with external knowledge (code/rag/).
• Prompt Engineering: Optimize LLM outputs (tutorials/prompt_engineering.md).
• Multimodal Applications: Text, image, audio integration (code/multimodal/).
• LangChain: Build LLM-powered apps (code/langchain/).

Details: part3_applications.md

Contribution Guidelines

Join us! See CONTRIBUTING.md for details.

References

• Building LLMs from Scratch
• LLMs from Scratch GitHub

Reading Materials

• LLM Engineers Handbook
• Attention Is All You Need (summary)