Share this link via
Or copy link
Overview
"Generative AI: Working with Large Language Models" is an in-depth course designed to introduce learners to the core principles, capabilities, and applications of large language models (LLMs) like GPT. Aimed at developers, data scientists, and AI enthusiasts, this course focuses on how to effectively work with and deploy LLMs in real-world contexts. You’ll gain a foundational understanding of how LLMs are trained, the architectures behind them (e.g., transformers), and the types of tasks they excel at—such as text generation, summarization, translation,...
Syllabus
Introduction
- Learning about Large Language Models
1. Transformers in NLP
- What are large language models?
- Transformers in production
- Transformers: History
2. Training Transformers and Their Architecture
- Transfer learning
- Transformer: Architecture overview
- Self-attention
- Multi-head attention and Feed Forward Network
3. Large Language Models
- GPT-3
- GPT-3 use cases
- Challenges and shortcomings of GPT-3
- GLaM
- Megatron-Turing NLG Model
- Gopher
- Scaling laws
- Chinchilla
- BIG-bench
- PaLM
- OPT and BLOOM
Conclusion
- Going further with Transformers
Instructor
Jonathan Fernandes
Reviews
No reviews yet. Be the first to review!
Alternative Courses
You must be logged in to submit a review.