Customizing Generative AI Models

Tune generative AI models through evaluation, RAG, and parameter-efficient finetuning. Foundations and prompt engineering for customization cover GenAI concepts, basic LLM application building,...

Read More
By Request
8781  Reviews star_rate star_rate star_rate star_rate star_half
$3,000USD
Duration 3 days
Course Code GAI-1201
Available Formats Classroom

Overview

Course Description

Tune generative AI models through evaluation, RAG, and parameter-efficient finetuning. Foundations and prompt engineering for customization cover GenAI concepts, basic LLM application building, automatic and dynamic prompt generation, troubleshooting refinements, and prompt engineering as a cheaper alternative to finetuning. Evaluation covers how GenAI evaluation differs from predictive AI, metrics across tasks and modalities, evaluation datasets, model benchmarking, and custom and chat-specific criteria. Retrieval-Augmented Generation covers embeddings, indexing, vector and full-text retrieval, filtering and reranking, and generation-time context. Parameter-efficient finetuning covers LoRA, IA3, prompt-tuning, and data augmentation across synthetic data, balance, evaluation, and bias. Hands-on labs produce an evaluation pipeline, a refined prompt set, a RAG implementation, a PEFT-finetuned model, and an agentic router. The course is designed for data scientists and software developers with Python, introductory generative-AI exposure, and familiarity with statistical metrics.

Skills Gained

By the end of this course, participants will be able to:

  • Evaluate generative AI models with metrics, datasets, and custom criteria
  • Apply prompt engineering as a customization layer over base models
  • Build retrieval-augmented generation pipelines for organization-specific data
  • Configure parameter-efficient finetuning techniques (LoRA, IA3, prompt-tuning)
  • Generate balanced, quality-evaluated synthetic data for PEFT workflows

Who Can Benefit

This course is designed for:

  • Data Scientists
  • Software Developers

Prerequisites

Participants should enter this course with:

  • Familiarity using Generative AI
  • Practical Python experience
  • Experience with statistical metrics (e.g., accuracy, precision, recall)

Organizational Objectives

This course assists organizations to:

  • Reduce model-tuning cost by reaching for prompt engineering and PEFT before full finetuning
  • Lower hallucination risk by grounding outputs in retrieval-augmented organization data
  • Build internal evaluation pipelines that catch model regressions before deploy
  • Establish a working knowledge of agentic AI patterns across the data-science team

Software

All attendees must have a modern web browser and an Internet connection.

Read Less

Course Details

Course Details

Module 1 - Understanding Generative AI

By the end of this module, you will be able to differentiate generative AI from traditional AI, describe how foundation models produce text and other modalities, and recognize the model settings and parameters that influence output quality.

  • Defining intelligence, artificial intelligence, and generative AI
  • Differentiating generative AI from traditional AI
  • How generative AI works (tokenization, embeddings, decoding)
  • Benefits and challenges of generative AI
  • Popular GenAI models and frameworks
  • LLM settings and parameters; intro to prompt engineering, RAG, and agentic AI
  • Hands-on Lab: Explore tokenization, embeddings, and core LLM settings hands-on without writing any code.

Module 2 - Basics of Prompt Engineering

By the end of this module, you will be able to write structured prompts using the CLEAR and RCTO/RTF frameworks, iterate prompts through a deliberate loop, and decompose tasks into sequenced prompts with human checkpoints between stages.

  • CLEAR framework
  • RCTO / RTF structure
  • Adaptive iteration loop
  • Workflow decomposition (analyze/transform/write)
  • Human checkpoints between stages
  • Prompt-vs-workflow-vs-tool decision
  • Hands-on Lab: Author and iterate one effective ChatGPT prompt that uses CLEAR and at least one n-shot variant for a workplace task.

Module 3 - Building Simple LLM-Based Applications

By the end of this module, you will be able to call LLMs through hosted APIs, structure prompts with prompt templates, build a conversational completion loop, and choose between closed-weight and open-weight models for cost and latency tradeoffs.

  • Application design building blocks
  • Accessing LLMs via APIs
  • Prompt templates
  • Conversational model of completion
  • Closed-weight vs. open-weight models
  • Batch APIs for cost control
  • Hands-on Lab: Build a vanilla chatbot against the OpenAI API using a prompt template and a conversational completion loop.

Module 4 - Evaluating Generative AI Models

By the end of this module, you will be able to design evaluation pipelines for generative AI, choose metrics that fit the task and modality, build evaluation datasets, and benchmark candidate models against custom and chat-specific criteria.

  • Generative AI evaluation vs. predictive AI evaluation
  • Generative AI evaluation metrics and techniques
  • Model comparison and benchmarking
  • Building and selecting evaluation datasets
  • Evaluating custom criteria
  • Chat-specific evaluation metrics
  • Hands-on Lab: Evaluate one LLM against custom criteria using DeepEval and G-Eval on a benchmark dataset.

Module 5 - Prompt Engineering for Customization

By the end of this module, you will be able to apply prompt engineering theory to modify model behaviour, evaluate prompt effectiveness with measurable criteria, automate and dynamically generate prompts, and troubleshoot prompts that drift in production.

  • Theory of prompt engineering
  • Modifying model behaviour with prompts
  • Evaluating the effectiveness of prompts
  • Automatic prompt engineering
  • Dynamic prompt generation
  • Troubleshooting and refining prompts
  • Hands-on Lab: Evaluate, refine, and dynamically generate prompts for a customized model task.

Module 6 - Basics of Retrieval Augmented Generation

By the end of this module, you will be able to build a RAG pipeline end-to-end — preparing and chunking documents, generating embeddings, retrieving with vector and full-text search, applying filtering and reranking, and providing context to the LLM at generation time.

  • Embeddings and the RAG phases: indexing, retrieval, generation
  • Indexing — preparation, chunking, enrichment, and embeddings
  • Working with structured and unstructured documents
  • Retrieval — vector, full-text, and fusion
  • Filtering, reranking, and looping to improve retrieval
  • Generation — providing context to the LLM
  • Hands-on Lab: Implement a RAG pipeline with LangChain that enriches documents before indexing and reranks retrieval results.

Module 7 - Parameter-Efficient Finetuning Techniques

By the end of this module, you will be able to recognize when PEFT beats full finetuning, apply prompt-based and low-rank adaptation techniques, choose between LoRA, IA3, and prompt-tuning for a given task, and evaluate PEFT performance against the base model.

  • Parameter-efficient finetuning vs. traditional finetuning
  • Prompt-based methods of finetuning
  • Low-rank adaptation techniques
  • IA3 and other techniques
  • Selecting a PEFT technique
  • Evaluating PEFT performance
  • Hands-on Lab: Apply prompt-tuning with HuggingFace PEFT to harden one model against indirect prompt injection.

Module 8 - Augmenting Data for PEFT

By the end of this module, you will be able to generate synthetic data for parameter-efficient finetuning, balance synthetic and real data, evaluate synthetic data quality, and recognize and mitigate bias introduced through augmentation.

  • Generating synthetic data for PEFT
  • Leveraging scaling laws for data augmentation
  • Considerations for synthetic data
  • Balancing synthetic and real data
  • Evaluating the quality of synthetic data
  • Addressing bias in synthetic data
  • Hands-on Lab: Generate synthetic data for one finetuning task and evaluate its quality and bias before training.

Module 9 - Basics of Agentic AI with LangGraph

By the end of this module, you will be able to build agentic LLM applications with LangGraph, recognize common agentic patterns, coordinate multi-agent workflows, and handle errors that arise when agents call tools and each other.

  • LangGraph concepts and principles
  • Common agentic patterns
  • Multi-agent workflows
  • Agent communication and coordination
  • Error handling in agentic systems
  • Scaling agentic AI applications
  • Hands-on Lab: Build an agentic router and a ReAct agent with LangGraph that share a tool and coordinate via a shared state graph.

Schedule

Upcoming Course Dates

There are currently no scheduled dates for this course. If you are interested in this course, contact us with the form below.

Contact Information

FAQ

Does the course schedule include a Lunchbreak?

Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.

What languages are used to deliver training?

Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.

What does GTR stand for?

GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.

Does Ascendient Learning deliver group training?

Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.

What does vendor-authorized training mean?

As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.

Is the training too basic, or will you go deep into technology?

It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.

How up-to-date are your courses and support materials?

We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.

Are your instructors seasoned trainers who have deep knowledge of the training topic?

Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.

Do you provide hands-on training and exercises in an actual lab environment?

Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.

Will you customize the training for our company’s specific needs and goals?

We will work with you to identify training needs and areas of growth.  We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.

How do I get started with certification?

Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.

Will I get access to content after I complete a course?

You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.

How do I request a W9 for Ascendient Learning?

View our filing status and how to request a W9.

Reviews

Simply great training provider that I can go for updating/acquiring my skill sets.

I think the platform is very good and look forward to taking my next course in early October.

The training was great . But i expected some of the Networking concepts would be covered in this certification .

Instructor knew her stuff. Long time in the industry. Course was easy to follow and very informative.

Brandon was a great instructor. The virtual course materials and labs provided were very informative.