Principles of Large Language Models

SKILLS: NLP Techniques and Representations; Model Fine-Tuning and Deployment; Generative AI Applications

Course Fee - ₹ 1000

Registration Closed

Overview

This course introduces the foundations, architectures, training techniques, and applications of Large Language Models (LLMs) and Generative AI. Students will explore the evolution of Natural Language Processing (NLP), from classical methods such as N-gram models, Bag-of-Words, TF-IDF, Word2Vec, and Hidden Markov Models to modern deep learning architectures, including RNNs, LSTMs, GRUs, Transformers, GPT, BERT, T5, and BART. The course covers text preprocessing, tokenization, distributed training, optimization, and fine-tuning of pre-trained language models. It also addresses ethical issues, bias, fairness, and emerging trends in multimodal AI, vision-language models, and multilingual LLMs. Through theory and hands-on activities, students will gain practical skills to develop and deploy modern LLM-based AI applications responsibly.

START DATE

Jul 01 2026

END DATE

Oct 15 2026

Delivery Mode

Online

Duration

15 Hours

Type

Theory

Course Fee

₹ 1000

Credentials and Certification

1 Credit

Course Category Micro-Credentials (Advanced)

TARGET AUDIENCE UG Students and PG students from all disciplines

Digital Credential

indicating verified micro-credential completion.

RECOMMENDED FOR

Students exploring industry-relevent skills

Professionals planning to upskill and reskill

Faculty building digital deployment literacy

COURSE DELIVERY

Action-based learning materials with guided assessments and faculty support.

Course Outcomes

Our curriculum matches modern standard practices to provide exceptional training milestones.

Foundations of Large Language Models

Understand the evolution of Natural Language Processing and the core principles that power modern Large Language Models and Generative AI systems.

CORE KNOWLEDGE

NLP Techniques and Representations

Explore classical NLP methods including N-grams, Bag-of-Words, TF-IDF, Word2Vec, and Hidden Markov Models for text analysis.

NLP FUNDAMENTALS

Deep Learning Architectures

Learn the architecture and working principles of RNNs, LSTMs, GRUs, Transformers, GPT, BERT, T5, and BART models.

ADVANCED AI

Model Fine-Tuning and Deployment

Apply text preprocessing, tokenization, encoding, and fine-tuning techniques to adapt pre-trained language models for practical NLP applications.

PRACTICAL LEARNING

Scalable and Responsible AI

Evaluate distributed training strategies, optimization methods, scalability challenges, and ethical AI practices for responsible language model development.

RESPONSIBLE AI

Generative AI Applications

Design and implement practical NLP and Generative AI solutions while exploring multimodal, multilingual, and next-generation foundation models.

INDUSTRY READINESS

ELIGIBILITY CRITERIA

This course is intended for undergraduate and postgraduate students, researchers, and professionals interested in Artificial Intelligence, Machine Learning, Data Science, and Natural Language Processing. Students pursuing or holding a degree in Computer Science, Artificial Intelligence, Data Science, Information Technology, Electronics, or related engineering disciplines.

Course Instructor

Expert guidance from acclaimed industry professional leaders.

Dr. S. A. Sahaaya Arul Mary

Associate Professor

Dr. S. A. Sahaaya Arul Mary is an Associate professor in the Department of AI and Data Science Engineering, School of Engineering and Technology, CHRIST University, Bangalore, Karnataka, India. She has over 30 years of experience in teaching and more than 17 years of experience in research. She has more than 80 publications in various reputed journals and conferences. She is a reviewer in IEEE Access, IEEE Transactions on Reliability and Springer Journals. She has reviewed more than 50 research papers. She has guided 11 Ph.D. Scholars. She has received grants and completed projects for DST, Google and NVIDIA. She is a committed Professor & Researcher inspiring and motivating students by providing a thorough understanding of a variety of computer concepts.

Program Overview

Academic Curriculum

A meticulous, guided learning path engineered to transform your cloud engineering expertise.

Unit 1

Evolution of Large Language Models and NLP

Evolution of Large Language Models and NLP - Introduction to Language Models , N - Gram Models, BAG of words , Word to Vector , TF-IDF & Cosine similarity , Hidden Markov Model (HMM) - Part 1 , Hidden Markov Model (HMM) - Part 2.

Unit 2

Transformer Networks

Transformer Networks - Recurrent Neural Network (RNN) - part 1, Recurrent Neural Network (RNN) - part 2 , Long Short-Term Memory (LSTM) - Part 1, Long Short-Term Memory (LSTM) - Part 2, GRU (Gated Recurrent Unit), Transformers - Part 1, Transformers - Part 2, Transformers - Part 3, Transformers - Part 4, Generative Pretrained Transformer (GPT) - Part 1.

Unit 3

Understanding and Applying Bidirectional Models

Understanding and Applying Bidirectional Models - BERT - Part 1,BERT - Part 2, BERT - Part 3, Fine-Tuning - Part 1 , Fine-Tuning - Part 2, T5 (Text-to-Text Transfer Transformer) - Part 1, T5 (Text-to-Text Transfer Transformer) - Part 2 , BART - Part 1, BART - Part 2, BART - Part 3.

Unit 4

Training, Fine-Tuning, and Optimizing LLMs

Training, Fine-Tuning, and Optimizing LLMs - Data Preprocessing for LLMs , Removing Stopwords , Text Encoding, Pre-trained Tokenizers, Distributed Training Strategies - Data Parallelism, Model & Pipeline Parallelism, Hybrid Parallelism & Gradient Accumulation, Optimizer , Adam with Weight Decay, Fine-Tuning - Part – 1, Fine - Tuning - Part – 2, Challenges in Scaling LLMs.

Unit 5

Ethics, Evaluation, and Real-World Applications

Ethics, Evaluation, and Real-World Applications - Biases in Language Models and Their Sources - Part 1, Biases in Language Models and Their Sources - Part 2, Ethical Issues in the Use of LLMs - Part 1,Ethical Issues in the Use of LLMs - Part 2, Addressing Bias and Fairness in LLMs - Part 1, Addressing Bias and Fairness in LLMs - Part 2 , Addressing Bias and Fairness in LLMs - Part 3 .

Unit 6

Multimodal Models and Emerging Trends

Multimodal Models and Emerging Trends - Overview of Multimodal Learning , Architectures and Techniques for Building Multimodal AI Models, Vision-Language Models CLIP and Its Capabilities, Vision-Language Models DALL -E and Its Capabilities , GPT-4 and Other Modern AI Models, Multilingual LLMs and cross-lingual learning.