Generative AI with LLM

Gain foundational knowledge, practical skills, and a functional understanding of how generative AI works

Skills You Will Gain

LLM & Gen AI Lifecycle

Pretrained LLM

Fine tuning LLM

LLM Powered Applications

This course includes

Syllabus Overview

Generative AI with LLM

Dive into the latest research on Gen AI to understand how companies are creating value with cutting-edge technology

  • Introduction to Artificial Intelligence
    • Discussion on the evolution of AI technologies and their transformative impact across various industries.
  • Fundamentals of Generative AI and LLMs
    • Examination of different generative models, with a focus on the progression from early models to current advanced Large Language Models.
    • Overview of typical LLM tasks such as text completion, name entity recognition, and sentiment analysis.
  • Deep Dive into Transformer Architecture
    • Detailed analysis of the Transformer architecture, focusing on key components such as self-attention mechanisms, multi-head attention, and positional encoding.
    • Exploration of the impact of transformer models on the field of natural language processing.
  • Exploring the “Attention is All You Need” Paper
    • Comprehensive study and discussion on the seminal paper that introduced transformers, analyzing its methodology and conclusions.
  • Variants of Transformer Models
    • Overview of various transformer model adaptations such as GPT (Generative Pre-trained Transformer), BERT (Bidirectional Encoder Representations from Transformers), and T5 (Text-to-Text Transfer Transformer).
    • Comparative study of their architectures, training approaches, and use cases.
  • Prompt Engineering and Its Applications
    • Techniques for effective prompt design to steer LLM outputs.
    • Case studies on how prompt engineering affects model performance and output quality.
  • Instruction-Based Fine-Tuning
    • Methods for customizing LLMs to specific tasks or datasets through targeted instruction.
  • Parameter Efficient Fine-Tuning (PEFT) Techniques
    • In-depth look at PEFT methods including LoRA (Low-Rank Adaptation), Soft Prompts, and BitFit.
    • Hands-on exercises to apply these techniques to enhance model performance without extensive retraining.
  • Reinforcement Learning from Human Feedback (RLHF)
    • Detailed exploration of RLHF techniques, focusing on how they refine model outputs based on human feedback.
    • Practical sessions on implementing RLHF in training cycles.
  • Exploring Other Advanced Training Techniques
    • Techniques such as Adapter layers, model distillation, and hybrid approaches combining rule-based systems with LLM outputs.
  • Model Integration into External Applications
    • Technical approaches for embedding LLMs into existing software applications and workflows.
    • Demonstrations on the integration of LLMs with APIs and microservices.
  • Performance Optimization and Scalability
    • Strategies to optimize performance and scalability of LLMs in production environments.
    • Use of hardware accelerations such as GPU and TPU optimizations.
  • Project Development and Implementation
    • Comprehensive application of the techniques learned to develop a project from conception through to a final product.
    • Continuous mentorship and review sessions to guide project development.
  • Project Presentation and Review
    • Formal presentations of capstone projects to a panel of experts.
    • Peer reviews and feedback sessions to refine and improve projects.
  • Course Conclusion
    • Review and Future Directions
      • Recap of key concepts and techniques learned throughout the course.
      • Discussion on the future trends in AI and ongoing learning opportunities.

Transform Your Skills: Enroll Now to Learn AI with LLMs

“AI for Everyone” will help you understand how to build a sustainable AI strategy.

Scroll to Top