Generative AI with Large Language Models

Mark as Favorite Share
image

What Will You Learn?

Gain foundational knowledge, practical skills, and a functional understanding of how generative AI works
Dive into the latest research on Gen AI to understand how companies are creating value with cutting-edge technology
Instruction from expert AWS AI practitioners who actively build and deploy AI in business use-cases today

About This Course

Provider: Coursera
Format: Online
Duration: 16 hours to complete [Approx]
Target Audience: Intermediate
Learning Objectives: By completing this free course, you'll able to deeply understand generative AI, describing the key steps in a typical LLM-based generative AI lifecycle, from data gathering and model selection, to performance evaluation and deployment
Course Prerequisites: Basics of machine learning
Assessment and Certification: Earn a Certificate upon completion from the relevant Provider
Instructor: Amazon Web Services, DeepLearning.AI
Key Topics: Generative AI, LLMs, Large Language Models, Machine Learning, Python Programming
Topic Covered: 
  2. - Course Introduction
  3. - Generative AI & LLMs
  4. - LLM use cases and tasks
  5. - Text generation before transformers
  6. - Transformers architecture
  7. - Generating text with transformers
  8. - Prompting and prompt engineering
  9. - Generative configuration
  10. - Generative AI project lifecycle
  11. - Introduction to AWS labs
  12. - Pre-training large language models
  13. - Computational challenges of training LLMs
  14. - Optional video: Efficient multi-GPU compute strategies
  15. - Scaling laws and compute-optimal models
  16. - Instruction fine-tuning
  17. - Fine-tuning on a single task
  18. - Multi-task instruction fine-tuning
  19. - Model evaluation
  20. - Benchmarks
  21. - Parameter efficient fine-tuning (PEFT)
  22. - PEFT techniques 1: LoRA
  23. - PEFT techniques 2: Soft prompts
  24. - Aligning models with human values
  25. - Reinforcement learning from human feedback (RLHF)
  26. - RLHF: Obtaining feedback from humans
  27. - RLHF: Reward model
  28. - RLHF: Fine-tuning with reinforcement learning
  29. - Optional video: Proximal policy optimization
  30. - RLHF: Reward hacking
  31. - Scaling human feedback
  32. - Lab 3 walkthrough
  33. - Model optimizations for deployment
  34. - Generative AI Project Lifecycle Cheat Sheet
  35. - Using the LLM in applications
  36. - Interacting with external applications
  37. - Helping LLMs reason and plan with chain-of-thought
  38. - Program-aided language models (PAL)
  39. - ReAct: Combining reasoning and action
  40. - LLM application architectures
  41. - Optional video: AWS Sagemaker JumpStart
  42. - Responsible AI

0 Comments

No reviews yet !!

Please login first

Course Tags
Generative AI Course Generative AI Free Course Top Free Course Generative AI with Large Language Models Responsible AI Free AI Course AI Course