Mastering Generative AI (Exploring the Frontiers of Generative & Agentic Models)Course ContentDuration: 2 Days (14-16 HRS)Eligibility: Can be joined by both engineering and biomedical and other students also who are interested in making their career and want to update in AI. (Open to All) Introduction to Generative AI: Get to know about what GenAI is.Difference between AI, Machine Learning & Deep Learning Difference between Discriminative AI vs Generative AI Tools involved in GenAIKnow about privileged GenAI tools and models.Effective roadmapto explore the GenAI model.Generative Architecture Introduction to Generative Adversarial Network (GAN) ArchitectureKnow about the Generator & Discriminator ModelsHow GAN architecture is uses for deepfake modelsDifference between Variational Auto Encoders (VAEs) vs GAN architecture Hands-on: Development of Generative Images using GAN Complex Architecture Hands-on: Create your own “Deep Fake Model” using low-level GAN Structure. Deep insights of GAN applications & drawbacks of it.Attention Is All You Need – Transformers & LLMs What is a transformer? What does the architecture look like? Text Generation before transformersKnow about the attention model vs. the multi-head attention model vs. the scaled dot-product attention difference between encoder & decoder architecture. Difference between Batch vs Layer NormalizationStep-into the most famous transformer community – Hugging FaceText Generation after transformersIntroduction to Large Language Models (LLMs)Popular LLMs: BERT, BART, DistilBertHands-on: Conversation AI using pre-trained LLM ModelHands-on: Image Caption Generator using pre-trained LLM Model Hands-on: Customized & Fine-tuning Question & Answering BERT Model Hands-on: Customized & Fine-tuning DistilBert ModelMastering Generative AI (Exploring the Frontiers of Generative Models) Learn about GPT (Generative Pre-trained Model).Fine-Tuning the LLM Model on a specific task & Model Evaluation Parameter Efficient Fine-Tuning (PEFT)Vision Transformer – ViT Model with API interfaceLearn about Vision Transformer Architecture and its variable components.Understand about image vectorisation, patch extraction & positional encoding.Hands-on: Pre-trained Google ViT Model for Image Classification Hands-on: Customized ViT architecture (RAW Structure for ViT Base) Hands-on: Create your own ViT multi-class classification and deploy the model into Hugging Face Hub using the API interface. Git workflowsGit cheat sheetReinforcement Learning From Human Feedback: Deep Insight of RLHFRLHF: Obtaining feedback from humans RLHF: Reward modelRLHF: Fine-tuning with reinforcement learningRelative Sync of ChatGPT with RLHFGenAI – LangChain Framework: What is LangChain?Usage of LangChain Framework? How does it work?Integrating the LangChain Framework with the LLM Model.Understand about the Langchain pipeline endpoints, chains & prompt templates.Hands-on: Create the simple LLM Langchain using the Hugging Face API InterfaceHands-on: Create the Langchain framework including the promptTemplate, AutoTokenizer & LLM Chain interfacing with the Hugging Face API interface.GenAI – Retrieval Augmented Generation (RAG) Explore the different tools in LangChain and initialise an agent that uses the tools to read different types of files or data present in the company databaseBuild the backend for the system using Vectorstore options present in LangChain Divide the documents into chunks and apply the LLM to create the embeddings. Extract entity for the chunks of document and store them in the VectorstoreConstruct the Search Index and Entity Store and create a functionality to update it with every question that the user asksUse the Chain functionality of LangChain to connect all the componentsHands-on: Create your simple RAG pipeline with FAISS Vector Store similarity search using the OpenAI API or the Hugging Face Endpoint API Interface. Hands-on: Create your own Retrieval QA End-to-End RAG pipeline using the OpenAI/Hugging Face API. GenAI Advanced – LangGraph & VectorDB/ChromaDB Build an agent from scratch, and understand the division of tasks between the LLM and the code around the LLM.Integrate agentic search capabilities to enhance agent knowledge and performance.Learn how agentic search retrieves multiple answers in a predictable format, unlike traditional search engines that return links.Incorporate human-in-the-loop into agent systemsHands-on: Create your own retrieval pipeline using ChromaDB to store the pdf embedding chunks. Add-on: Hugging Spaces – Knowledge to deploy How to use the Llama & other popular LLM models in Hugging Face Spaces. How to create the new workspace and initialise your repository?Hands-on: Build and deploy your own GenAI application in Hugging Face Spaces using Streamlit. Professional NetworkingConnect with industry experts and fellow professionalsStay updated with the latest tools, trends and hiring insightsCertificationAll participants will receive a globally recognized hardcopy certificate after the workshop.Eligibility:Open to AllB.Tech, B.E., M.B.B.S., BCA, MCA, MS, MD, B.Sc IT, M.Sc IT, Biomedical, Biotechnology, BBA, MBA, B.A., hobbyists and more.Key Benefits:✔️ Hands-on workshop with real-world use cases✔️ Industry-driven curriculum✔️ Exposure to leading tech tools and AI applications✔️ Mentorship from domain experts✔️ Networking opportunities with professionals
Also check out other Workshops in Aurangabad.
