Cohort 2

Gain a thorough understanding of the world of Large Language Models with a deep understanding on how to build your own applications

Hamza Farooq

Founder | Ex-Google |
Adjunct Professor Stanford & UCLA

Building LLM Applications

Google

University of Minnesota

Stanford University

This course is amongst the top-rated technical courses and I am proud to say it's an extremely popular course So far I have taught this course to over 300 Professional. The course is aimed to introduce you to Large Language Models in deeper detail on what is Transformer Architecture and how we utilize the Encoder and Decoder Models. This is not a Langchain course but much more than that. We go into great depth to explain the building blocks of retrieval systems and how to utilize Open Source LLMs to build your own RAG-based architectures. Learning Outcome: - Gain a comprehensive understanding of the end-to-end LLM architecture - Construct and deploy robust and effective models in real-world settings using LargeLanguage Models.&nbsp; - Learn to tackle practical machine learning problems and deliver results in production. Additionally, students will gain a comprehensive understanding of the end-to-end machine learning pipeline, allowing them to construct and deploy robust and effective models in real-world settings using Large Language Models. Overall, students will emerge with greater confidence in their abilities to tackle practical machine learning problems and deliver results in production. Please Note:This is not a beginner course for non technical people, it requires knowledge of Python and some basic machine learning background.

Build LLM Powered Applications, like a pro!

You are intrigued about LLMs and would like to build applications powered by LLMs

You are ready to deploy your own SOTA AI Models and like to see how they work

You want to go beyond Jupyter Notebook and develop batch or real-time prediction

Who is this course for

What you’ll get out of this course

Collect and preprocess data for large language models

Train and fine-tune pre-trained large language models for specific tasks

Evaluate the performance of large language models and select appropriate metrics

Deploy large language models in real-world applications using APIs and Huggingface

Understand ethical considerations involved in working with large language models, such as avoiding bias and ensuring transparency

<ol><li>Introduction to NLP: covers what NLP is, its history, applications and challenges.</li><li>NLP Techniques: covers common techniques such as tokenization, part-of-speech tagging, named entity recognition and sentiment analysis with examples of their use.</li><li>NLP Tools: introduces popular NLP tools such as NLTK, spaCy with examples of how to use them </li></ol>

Introduction to Natural Language Processing

<ol><li>Transformers Foundational Knowledge: covers fundamental concepts of transformers, including self-attention, multi-head attention, and positional encoding.</li><li>Introduction to Fundamental Concepts of ML System Design: covers the basics of designing machine learning systems, including data collection and preprocessing, model selection and training</li></ol>

Foundational Knowledge of Transformers & ML System Design

<ol><li>Introduction to Information Retrieval Systems: covers the basic concepts and goals of information retrieval systems and their importance in various applications.</li><li>FAISS: introduces Facebook's AI Similarity Search (FAISS) library, a popular open-source library for efficient similarity search and clustering of dense vectors, and explains how it works.</li></ol>

Retrieval Systems

<ol><li>Deployment on a Serverless Inference: discusses the benefits of serverless computing and how to deploy the semantic search model on a serverless platform like Huggingface</li><li>Preprocessing of Hotel Data</li><li>Evaluation of the Model: discusses the different evaluation metrics used for semantic search models and how to measure the performance of the model</li></ol>

Building a search engine from bare bones and deploying it on Huggingface using server-less inference

<ol><li>Introduction to Knowledge Graph: covers the basics of knowledge graphs, including their architecture, data modeling, and how they are used in real-world applications like search engines and recommendation systems.</li><li>Generative AI: introduces the concept of generative AI and how it is used to generate new data, such as text, images, and music. </li></ol>

Knowledge Graph, Generative AI, Alpaca,Llama and Dolly 2.0 and World of langchain on larger corpus of Data

<ul><li>Understand the difference between prompt engineering and fine tuning</li><li>Introducing bits and bytes</li><li>Fine tuning GPT3</li></ul>

Fine tuning Models using PeFT and QLoRa

Teams get to present their learnings through a capstone project

Demo Day

Course syllabus

Data Scientist & Career Coach at Data Sistah

What people are saying

Excited to have you here

We will go through each module during this class

Saturday: Module Teaching

Students will spend time building projects with their team members or individually

Weekly projects

Course schedule

This course builds on live workshops and hands-on projects

Active hands-on learning

You’ll be interacting with other learners through breakout rooms and project teams

Interactive and project-based

Join a community of like-minded people who want to learn and grow alongside you

Course completed by

About this course

Get notified about the next cohort

Learn from live sessions