Developing Your Own GPT Model with Python

Preference Dates Timing Location Registration Fees
Weekdays program (in-person and live online) February 17 - 21, 2025 9:00 AM - 4:00 PM (GMT+4) Dubai Knowledge Park 3675 USD

Course Description

This course is designed to guide participants through the entire process of working with Large Language Models (LLMs) like GPT-2, LLaMA, and Falcon, from fine-tuning to deployment. By the end of this course, participants will have the skills to fine-tune open-source LLMs with their own data, deploy these models on a Google Cloud VM, and create a user interface using Django to interact with the models via prompts. This hands-on, project-based course will equip participants with the knowledge to build and deploy a fully functional GPT-like chatbot.

Upon successful completion of this program the participants will earn a certificate accredited by Dubai Government.

Click Here to Register

Module 1 – Introduction to LLMs & Setup

  • Overview of LLMs and today’s open-source landscape (Mistral, LLaMA, Falcon)
  • Installing Python, PyTorch, Hugging Face libraries
  • Running your first chatbot on an NVIDIA GPU

Module 2 – Prompt Engineering & Customization

  • Understanding effective prompts for domain-specific assistants
  • Prompt tuning vs. fine-tuning (when and why)
  • Hands-on: Experimenting with different prompting strategies

Module 3 – Data Collection & Preprocessing

  • Collecting and cleaning organizational data (PDF, CSV, TXT)
  • Chunking text for use in LLM pipelines
  • Basics of tokenization and embeddings

Module 4 – Working with Embeddings & Vector Databases

  • Introduction to embeddings and vector search
  • Storing data in FAISS (vector DB)
  • Querying your private data with similarity search

Module 5 – Building a RAG (Retrieval-Augmented Generation) Pipeline

  • Combining LLM + FAISS for contextual answers
  • Passing retrieved context into prompts
  • Testing your first RAG-powered chatbot

Module 6 – From Chatbot to AI Agent

  • What makes an AI agent different from a chatbot
  • Building tools and APIs for agents
  • Using LangChain to enable real-world actions (e.g., schedule queries)

Module 7 – Deployment with Django

  • Building a simple web interface for your chatbot/agent
  • Connecting backend inference to the UI
  • Running locally and testing with users

Module 8 – Scaling & Production Readiness

  • Deploying with Docker & Kubernetes
  • Monitoring and securing AI deployments
  • Future directions: multimodal models (text, images, and audio)

Target Audience

  • Software Developers: Build and deploy AI-powered chatbots and agents.
  • Data Scientists: Fine-tune and integrate LLMs into real-world workflows.
  • Data Analysts: Enhance analysis and insights with AI-driven tools.
  • AI Enthusiasts: Gain hands-on experience creating chatbots and agents.
  • Professionals Curious About Generative AI: Learn to apply LLMs and agents in practice.

Prerequisites for this Course

  • Comfortable with Python programming, including writing scripts and managing Python packages.
  • Experience with Python libraries commonly used in data science (e.g., NumPy, Pandas) is advantageous.
  • Foundational understanding of AI and data science concepts, such as machine learning basics, data preprocessing, and model training and evaluation.

Learning Objectives

  • Run and customize state-of-the-art open-source LLMs such as Mistral and LLaMA.
  • Integrate private data into chatbots using Retrieval-Augmented Generation (RAG).
  • Develop AI agents capable of performing real-world tasks with LangChain.
  • Build and deploy user-facing applications with Django.
  • Scale and secure AI systems using Docker and Kubernetes.
  • Understand future directions in Generative AI, including multimodal models.
Click Here to Register