Learn · NPTEL

Course10610257637 lectures

Introduction to Large Language Models (LLMs)

Prof. Tanmoy Chakraborty and Prof. Soumen Chakraborti · IIT Delhi IIT Bombay

Start with lecture 1 At NPTEL

About

This course introduces the fundamental concepts underlying Large Language Models (LLMs). It starts with an introduction to the various problems in NLP, and discusses how to approach the problem of language modeling using deep learning. It describes the architectural intricacies of Transformers and the pre-training objectives of the different Transformer-based models. It also discusses the recent advances in LLM research, including LLM alignment, prompting, parameter-efficient adaptation, hallucination, bias and ethical considerations. This course prepares a student to comprehend, critique and approach various research problems on LLMs.

Intended audience: UG and PG students in CSE, EE, ECE, IT, Maths, etc.

Prerequisites: Mandatory: Machine Learning, Python Programming Optional: Deep LearningIntroduction To Machine Learning: https://nptel.ac.in/courses/106105152Python for Data Science: https://nptel.ac.in/courses/106106212

Lectures

Week 1

  1. Lec 01 : Introduction and Recent Advances YouTube
  2. Lec 02 : Introduction to Natural Language Processing YouTube

Week 2

  1. Lec 03 : Introduction to Statistical Language Models YouTube
  2. Lec 04 : Statistical LM: Advanced Smoothing and Evaluation YouTube

Week 3

  1. Lec 05 : Introduction to Deep Learning YouTube
  2. Lec 06 : Introduction to PyTorch YouTube

Week 4

  1. Lec 07 : Word Representation: Word2Vec & fastText YouTube
  2. Lec 08 : Word Representation: GloVe YouTube
  3. Lec 09 : Tokenization Strategies YouTube

Week 5

  1. Lec 10 : Neural Language Models: CNN & RNN YouTube
  2. Lec 11 : Neural Language Models: LSTM & GRU YouTube
  3. Lec 12 : Sequence-to-Sequence Models YouTube
  4. Lec 13 : Decoding Strategies YouTube
  5. Lec 14 : Attention in Sequence-to-Sequence Models YouTube

Week 6

  1. Lec 15 : Introduction to Transformer: Self & Multi-Head Attention YouTube
  2. Lec 16 : Introduction to Transformer: Positional Encoding and Layer Normalization YouTube
  3. Lec 17 : Implementation of Transformer using PyTorch YouTube

Week 7

  1. Lec 18 : Pre-Training Strategies: ELMo, BERT YouTube
  2. Lec 19 : Pre-Training Strategies: Encoder-decoder and Decoder-only Models YouTube
  3. Lec 20 : Introduction to HuggingFace YouTube

Week 8

  1. Lec 21 : Instruction Tuning YouTube
  2. Lec 22 : Prompt-based Learning YouTube
  3. Lec 23 : Advanced Prompting and Prompt Sensitivity YouTube
  4. Lec 24 : Alignment of Language Models-I YouTube
  5. Lec 25 : Alignment of Language Models-II YouTube

Week 9

  1. Lec 26 : Knowledge and Retrieval: Knowledge Graph YouTube
  2. Lec 27 : Knowledge and Retrieval: Knowledge Graph Completion and Evaluation YouTube
  3. Lec 28 : Knowledge and Retrieval: Translation and Rotation Models YouTube

Week 10

  1. Lec 29 : Parameter Efficient Fine-Tuning (PEFT) YouTube
  2. Lec 30 : Quantization, Pruning & Distillation YouTube
  3. Lec 31 : An Alternate Formulation of Transformers: Residual Stream Perspective YouTube
  4. Lec 32 : Interpretability Techniques YouTube

Week 11

  1. Lec 33 : Knowledge and Retrieval: Multiplicative models YouTube
  2. Lec 34 : Knowledge and Retrieval: Modeling Hierarchies YouTube
  3. Lec 35 : Knowledge and Retrieval: Temporal Knowledge Graphs YouTube

Week 12

  1. Lec 36 : Responsible LLMs YouTube
  2. Lec 37 : Conclusion: Expert Panel Discussion YouTube

Syllabus and materials

At NPTEL, as the course publishes them.

Credits and licence

Institution
IIT Delhi IIT Bombay
Department
Computer Science and Engineering
Taught by
Prof. Tanmoy Chakraborty, Prof. Soumen Chakraborti
Level
Undergraduate
Language
English
Subjects
Computer science, Engineering
Source
NPTEL
Licence
CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
Attribution
NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge. Coordinated by IIT Delhi.
Who can watch
NPTEL gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed