Course10610257637 lectures
Introduction to Large Language Models (LLMs)
Prof. Tanmoy Chakraborty and Prof. Soumen Chakraborti · IIT Delhi IIT Bombay
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
Week 2
- Lec 03 : Introduction to Statistical Language Models
- Lec 04 : Statistical LM: Advanced Smoothing and Evaluation
Week 3
Week 4
- Lec 07 : Word Representation: Word2Vec & fastText
- Lec 08 : Word Representation: GloVe
- Lec 09 : Tokenization Strategies
Week 5
- Lec 10 : Neural Language Models: CNN & RNN
- Lec 11 : Neural Language Models: LSTM & GRU
- Lec 12 : Sequence-to-Sequence Models
- Lec 13 : Decoding Strategies
- Lec 14 : Attention in Sequence-to-Sequence Models
Week 6
- Lec 15 : Introduction to Transformer: Self & Multi-Head Attention
- Lec 16 : Introduction to Transformer: Positional Encoding and Layer Normalization
- Lec 17 : Implementation of Transformer using PyTorch
Week 7
- Lec 18 : Pre-Training Strategies: ELMo, BERT
- Lec 19 : Pre-Training Strategies: Encoder-decoder and Decoder-only Models
- Lec 20 : Introduction to HuggingFace
Week 8
- Lec 21 : Instruction Tuning
- Lec 22 : Prompt-based Learning
- Lec 23 : Advanced Prompting and Prompt Sensitivity
- Lec 24 : Alignment of Language Models-I
- Lec 25 : Alignment of Language Models-II
Week 9
- Lec 26 : Knowledge and Retrieval: Knowledge Graph
- Lec 27 : Knowledge and Retrieval: Knowledge Graph Completion and Evaluation
- Lec 28 : Knowledge and Retrieval: Translation and Rotation Models
Week 10
- Lec 29 : Parameter Efficient Fine-Tuning (PEFT)
- Lec 30 : Quantization, Pruning & Distillation
- Lec 31 : An Alternate Formulation of Transformers: Residual Stream Perspective
- Lec 32 : Interpretability Techniques
Week 11
- Lec 33 : Knowledge and Retrieval: Multiplicative models
- Lec 34 : Knowledge and Retrieval: Modeling Hierarchies
- Lec 35 : Knowledge and Retrieval: Temporal Knowledge Graphs
Week 12
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
More like this
Course
Matrix Methods in Data Analysis, Signal Processing, and Machine Learning
34 lectures · Video
Course
Computational Science and Engineering I
50 lectures · Video
Course
Engineering Dynamics
223 lectures · Video
Course
CS50’s Introduction to Computer Science
12 lectures · Video
Course
Frontiers of Biomedical Engineering
25 lectures · Audio
Course
CS50's Introduction to Programming with Python
10 lectures · Video