Generative AI with LLMs Certification

About Course

The Generative AI with LLMs Certification equips learners with expertise in Large Language Models (LLMs) like GPT, BERT, and LLaMA. It covers NLP fundamentals, prompt engineering, fine-tuning, model deployment, and real-world applications in automation, chatbots, and content creation. Participants gain hands-on experience with AI tools, frameworks like TensorFlow and PyTorch, and cloud-based AI services. The certification enhances problem-solving, data analysis, and AI development skills, making candidates industry-ready. Ideal for developers, data scientists, and AI enthusiasts, this program ensures proficiency in leveraging generative AI for business, research, and innovation.

Course Content

Module 1- Generative AI and LLM Essentials

Understanding Generative AI
Applications of Generative AI
Types of Generative Models: GANs, VAEs, Autoregressive models
Introduction to Large Language Models (LLMs)
Transformer Architecture
Exploring different Opensource LLMs
Introduction to HuggingFace and its Pre-trained LLM Models
Limitations of LLMs
Advantages and Disadvantages of Different LLM Architectures
Accessing and Using Open-Source LLMs for Projects
Responsible AI Development Practices

Module 2-Prompting Techniques for Generative Models

Prompt Engineering Principles
What is Prompt Engineering?
Concept and relevance of prompt engineering in generative AI models
Explore commonly used tools for prompt engineering
Prompt Design Strategies
Types of Prompting
Approaches for writing effective prompts
Best practices for creating impactful prompts
Parameter Tuning

Module 3-Interacting with Data using Retrieval-Augmented Generation

Understanding RAG
RAG Architecture
Retriever Techniques
Keyword Matching
Sentence Transformers
LLM Integration with Prompt and Retrieved Information
Augmentation Strategies
Benefits of RAG
Access to Real-time Information
Improved Grounding and Factual Accuracy
Advanced RAG: Moving Beyond Naive RAG
Modular RAG
Retrieval Quality Enhancement

Module 4-LLMs for Word Embedding and Chunking Mechanism

Word Embedding Introduction
Word Embedding Techniques
Capturing Word Relationships
Sentence Embedding Techniques
Introduction to Vector Databases
Different Types of Vector Databases
Chunking
Perform Chunking of the Document
Traditional Chunking mechanism
Advanced Chunking Mechanism
Character Splitting
Recursive Character splitting
Document-based Chunking
Semantic Chunking
Agentic Chunking

Module 5-LangChain and LlamaIndex for LLM Application Development

Module 6-Fine Tuning and Evaluating Generative Models

Fine-Tuning Fundamentals
Fine-Tuning Techniques for Generative Models
Data augmentation
Hyperparameter Tuning
Curriculum Learning
Transfer Learning PEFT (Parameter-Efficient Fine-Tuning)
Low-Rank Adaptation (LoRA)
Quantized LoRA (QLoRA)
Feature Extraction
Full Fine-Tuning
Selective Fine-Tuning
Multi-Task Learning
Reinforcement Learning from Human Feedback
Challenges of Evaluating Generative Models
Inception Score
BLEU score
ROUGE score
Qualitative Evaluation

Module 7-Generative AI on Cloud

Add this certificate to your resume to demonstrate your skills & increase your chances of getting noticed.

About Course

What Will You Learn?

Course Content

Module 1- Generative AI and LLM Essentials

Understanding Generative AI

Applications of Generative AI

Types of Generative Models: GANs, VAEs, Autoregressive models

Introduction to Large Language Models (LLMs)

Transformer Architecture

Exploring different Opensource LLMs

Introduction to HuggingFace and its Pre-trained LLM Models

Limitations of LLMs

Advantages and Disadvantages of Different LLM Architectures

Accessing and Using Open-Source LLMs for Projects

Responsible AI Development Practices

Module 2-Prompting Techniques for Generative Models

Prompt Engineering Principles

What is Prompt Engineering?

Concept and relevance of prompt engineering in generative AI models

Explore commonly used tools for prompt engineering

Prompt Design Strategies

Types of Prompting

Approaches for writing effective prompts

Best practices for creating impactful prompts

Parameter Tuning

Module 3-Interacting with Data using Retrieval-Augmented Generation

Understanding RAG

RAG Architecture

Retriever Techniques

Keyword Matching

Sentence Transformers

LLM Integration with Prompt and Retrieved Information

Augmentation Strategies

Benefits of RAG

Access to Real-time Information

Improved Grounding and Factual Accuracy

Advanced RAG: Moving Beyond Naive RAG

Modular RAG

Retrieval Quality Enhancement

Module 4-LLMs for Word Embedding and Chunking Mechanism

Word Embedding Introduction

Word Embedding Techniques

Capturing Word Relationships

Sentence Embedding Techniques

Introduction to Vector Databases

Different Types of Vector Databases

Chunking

Perform Chunking of the Document

Traditional Chunking mechanism

Advanced Chunking Mechanism

Character Splitting

Recursive Character splitting

Document-based Chunking

Semantic Chunking

Agentic Chunking

Module 5-LangChain and LlamaIndex for LLM Application Development

LangChain Framework

Chaining LLMs with other AI Components for Complex Workflows

Building Applications with Combined Functionalities

LlamaIndex for Large-Scale Factual Knowledge Indexing for LLMs

Module 6-Fine Tuning and Evaluating Generative Models

Fine-Tuning Fundamentals

Fine-Tuning Techniques for Generative Models

Data augmentation

Hyperparameter Tuning

Curriculum Learning

Transfer Learning PEFT (Parameter-Efficient Fine-Tuning)

Low-Rank Adaptation (LoRA)

Quantized LoRA (QLoRA)

Feature Extraction

Full Fine-Tuning

Selective Fine-Tuning

Multi-Task Learning

Reinforcement Learning from Human Feedback

Challenges of Evaluating Generative Models

Inception Score

BLEU score

ROUGE score

Qualitative Evaluation

Module 7-Generative AI on Cloud