Skip to main content
Ctrl+K
LLM Foundations - Home

Introduction

  • 1. Introduction: LLM in the Age of AI

LLM Foundations

  • 2. Language Models
  • 3. Early Neural Language Models
  • 4. Word Embeddings
  • 5. Transformers
  • 6. BERT
  • 7. Seq2Seq: T5 and BART
  • 8. GPT Series

LLM Architectures

  • 9. LLM Architecture Fundamentals
  • 10. MoE Sparse Architectures (WIP)

LLM Training

  • 11. LLM Training Fundamentals
  • 12. LLM Finetuning
  • 13. LLM Alignment and Preference Learning
  • 14. LLM Reasoning (WIP)
  • 15. LLM Training Acceleration (WIP)
  • 16. *Reinforcement Learning Essentials

LLM Case Studies

  • 17. Llama Series
  • 18. DeepSeek Series

LLM Inference

  • 19. Decoding
  • 20. Inference Acceleration (WIP)

Prompting

  • 21. Basic Prompting
  • 22. Advanced Prompting Techniques

Application in Information Retrieval and RAG

  • 23. Information Retrieval and Sparse Retrieval
  • 24. Information Retrieval and Dense Models
  • 25. Application of LLM in IR (WIP)
  • 26. RAG
  • 27. Advanced RAG (WIP)

Index

I | N

I

  • Information retrieval, [1], [2]
  • inverted index
  • IR, [1], [2]

N

  • Neural IR, [1], [2]

By Yuguang Yang

© Copyright 2023.