Generative AI: Defining the New World Order

Right now, people all over the world are going bonkers over something called ChatGPT. In this workshop, we’ll learn the basic concepts behind how ChatGPT works and then learn how to code, train, and use our own version of it from scratch using PyTorch. From this coding experience, we’ll learn about the strengths and weaknesses of models like ChatGPT, as well as discuss alternative design strategies. Then we’ll learn how to fine-tune a production language model on a custom dataset. Fine-tuning on a custom dataset gives us more control over how the model behaves and can make it more reliable.

NOTE: This workshop will be done in “StatQuest Style” meaning every little detail will be clearly explained. We’ll also start each module with a silly song.

Join us for an immersive workshop designed to unveil the essence of machine learning and enhance your technical prowess. This workshop covers everything from foundational concepts like regression and classification to advanced topics such as model evaluation and tree-based models. Dive into prompt engineering, explore linear and tree-based models, and master advanced ML workflows to elevate your data science skills to new heights.

Overview 

In today's rapidly evolving digital landscape, Retrieval-Augmented Generation (RAG) has emerged as a transformative technology, permeating various industries and shaping the future of artificial intelligence. RAG's ability to seamlessly integrate retrieval and generation capabilities has unlocked unprecedented possibilities, revolutionizing how we approach problem-solving, decision-making, and knowledge creation.

RAG is an AI framework that enhances the accuracy and reliability of large language models (LLMs) by allowing them to retrieve relevant information from external knowledge sources before generating a response. This helps ground the LLM's outputs in factual data, reducing the risk of hallucinating incorrect or misleading information.

Big Business Benefits of RAG

• Access to Reliable Information: RAG ensures LLMs access current, credible facts, allowing users to verify sources.
• Dynamic Data Integration: RAG integrates new data seamlessly, reducing the need for frequent retraining.
• Cost Efficiency: RAG lowers computational and financial burdens compared to constant retraining.
• Improved Response Accuracy: RAG enhances LLMs' ability to recognize and probe for more details, ensuring accurate responses.

Welcome to the "Building GenAI Applications Using RAG" workshop, a comprehensive journey from absolute beginner to advanced RAG application developer. Throughout this immersive experience, participants will progress from foundational concepts to building sophisticated RAG systems, all driven by hands-on learning. 

The workshop begins by demystifying the evolution of Generative AI and clarifying key terms, guiding even novices through the complex landscape. Participants will explore various GenAI approaches, equipping them with the knowledge to make informed decisions for their specific business applications. From there, attendees dive into the heart of RAG, starting with tokenization and advancing to building practical RAG applications using Langchain. Each step is hands-on, ensuring tangible outcomes and solid takeaways. As the day unfolds, participants master advanced retrieval strategies, query expansion, and evaluation techniques, honing their skills for real-world application. Bonus topics on super-advanced concepts await, time permitting. 

Through this workshop, participants emerge with the confidence and capability to navigate the complexities of Generative AI, from theory to application, and get started on a transformative journey toward becoming confident RAG developers.

Prerequisite: Basic knowledge of Python, Fundamentals of Transformers Architecture (nice to have)

This workshop is designed to provide a comprehensive overview of LLMs, from foundational concepts to advanced applications. Whether you're a beginner or have intermediate experience, you will gain valuable insights and hands-on experience with some of the most cutting-edge technologies in the field.

• Key Takeaways:
  • Understand the fundamentals of Language Models and Transformer architectures.
  • Gain hands-on experience with LLMs and related concepts such as PEFT, Prompt Engineering, RAGs, and more.
  • Explore advanced topics such as Reinforcement Learning from Human Feedback (RLHF) and Retrieval-Augmented Generation (RAG).

LLMs have taken the world by storm since their inception, and the past year has marked a significant shift in the AI industry and its impact on our day-to-day lives.

As an engineer working on LLMs, tackling the challenges of collaborating, training, scaling, and monitoring such massive models has become increasingly complex. LLMOps encompasses the practices, techniques, and tools necessary for the operational management of large language models in production. It's the infrastructure created by LLMOps that drives efficiency, agility, security, and scalability for both its engineers and end-users.

Join us in this immersive LLMOps workshop, where we'll embark on a day-long journey, delving into various modules crafted to equip you with actionable insights and hands-on skills to harness the full potential of LLMs.

Prerequisite: AWS Account with Sagemaker, EKS and Bedrock full access

By the end of the workshop you will be able to:

• Explore how AI can reshape your business landscape, identify potential AI projects, and create value.
• Understand different AI technologies, including Machine Learning, Deep Learning, Natural Language Processing (NLP), Computer Vision, Generative AI, and their application in various business scenarios.
• Explore to formulate a clear AI strategy that aligns with your business goals, considering scalability, sustainability, and ethical implications.
• Discuss about best practices for implementing AI projects, including data collection, model training, evaluation, and deployment.
• Learn about the critical roles needed in an AI team and the key competencies required.
• Understand how to attract, develop, and retain AI talent in the age of disruptive technologies like Generative AI.

Have you ever used groundbreaking technologies such as MidJourney and Stable Diffusion for your professional and personal work? I am sure you did. These technologies have taken the world by storm and have become part of our lives. Wondering how these technologies work and what makes them so incredibly effective? The answer lies in the power of Diffusion Models.

The diffusion models have become the backbone of modern computer vision! From Dall-E 2 to Midjourney, these powerful models have revolutionized the way machines understand and process information. But what exactly are Diffusion Models, and how do they work? Don’t worry! You are at the right place. Welcome to the workshop on Diffusion models!

In this workshop, you will get a comprehensive introduction into the world of training and fine-tuning Large Language Models (LLMs) and Generative AI. Over the course of five modules, you will explore the essentials of LLMs, deep-dive into training and fine-tuning methodologies, and learn about parameter-efficient techniques like Low rank Adaptation (LoRA), Quantized low rank Adaptation (QLoRA) and instruction-based fine-tuning using techniques like Supervised Fine-tuning and Reinforcement Learning with Human Feedback. You will also learn about the advantages, disadvantages and best practices for these techniques. This is not a university lecture. We will follow a hybrid approach where you will learn the concepts behind these techniques and also spend a lot of time with live hands-on sessions, actually training and fine-tuning LLMs using tools like the HuggingFace ecosystem and Unsloth AI.

Additional Points:

• Prerequisites: Basic understanding of Python, NLP and Deep Learning is helpful
• Content Provided: Slides, complete code notebooks, datasets
• Infrastructure: We will be running everything on the cloud on a GPU server, you will be provided with runpod.io credits or you can use Colab for some of the hands-on also
• Important Note: Some of the hands-on, especially SFT and RLHF on LLMs usually take a minimum of 30+ hours so we might pre-run some of them and do a live walkthrough. Rest most of the hands-on everyone can run live along with the instructor in the session
• Session will be interactive so feel free to keep it interesting and ask questions and treat it as a open-ended discussion

In this workshop, you'll journey through Reinforcement Learning (RL), starting with fundamental concepts and advancing to complex techniques, focusing on real-world applications. Time permitting, you'll also explore how Large Language Models (LLMs) can optimize RL reward functions in a human-centric manner. Whether you're a seasoned AI professional or just beginning, this workshop equips you with the skills and knowledge to tackle real-world challenges using RL. 

Discover how cutting-edge technologies leverage Reinforcement Learning (RL) to achieve groundbreaking results! For instance, the revolutionary generative model ChatGPT utilizes RL techniques behind the scenes. The core principle driving ChatGPT is Reinforcement Learning from Human Feedback (RLHF), which aligns Large Language Models (LLMs) with human preferences. This demonstrates the immense potential of RL to solve real-world problems and transform industries. Join our workshop to harness the power of RL and become a part of the AI revolution!

Explore the evolution of Generative AI, enterprise applications, and the hardware essentials for large language models. Delve into Intel's AI-enhancing technologies, from Xeon® and Gaudi® AI Accelerators to the Core Ultra series. Engage in hands-on sessions optimizing inference and deploying AI models on Intel® Developer Cloud.