Details 

1. Collect and preprocess data for large language models

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

3. Evaluate the performance of large language models and select appropriate metrics

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

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

​

Learning Outcome:

Upon completing this course, students will undergo a transformation in their understanding of machine learning with a focus on production and LLMs. They will gain practical skills in building and deploying machine learning models in a production environment.

 

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.

​

Curriculum

​

01 - Introduction to Natural Language Processing

1. Introduction to NLP: covers what NLP is, its history, applications and challenges.

2. NLP Techniques: covers common techniques such as tokenization, part-of-speech tagging, named entity recognition and sentiment analysis with examples of their use.

3. NLP Tools: introduces popular NLP tools such as NLTK, spaCy with examples of how to use them

​

02 - Foundational Knowledge of Transformers & ML System Design

1. Transformers Foundational Knowledge: covers fundamental concepts of transformers, including self-attention, multi-head attention, and positional encoding.

2. 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

 

03 - Retrieval Systems

1. Introduction to Information Retrieval Systems: covers the basic concepts and goals of information retrieval systems and their importance in various applications.

2. 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.

​

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

1. Deployment on a Serverless Inference: discusses the benefits of serverless computing and how to deploy the semantic search model on a serverless platform like Hugging Face

2. Preprocessing of Hotel Data

3. Evaluation of the Model: discusses the different evaluation metrics used for semantic search models and how to measure the performance of the model

​

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

1. 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.

2. Generative AI: introduces the concept of generative AI and how it is used to generate new data, such as text, images, and music.

​

06 - Deploying models in Airflow, DAGs and using GPU-as-a-service to build automated systems [replicate.ai & banana.dev]

Details to follow...

​​