This repository contains materials and notes from the Generative AI with LLMs course offered by Coursera. The course provides a comprehensive understanding of how generative AI works and how it can be deployed in real-world applications. It emphasizes practical intuition and best practices for utilizing large language models (LLMs).
By completing this course, learners gain skills to:
- Understand the generative AI lifecycle, from data gathering and model selection to performance evaluation and deployment.
- Describe the transformer architecture that powers LLMs and explain training and fine-tuning techniques for specific use cases.
- Optimize model performance using empirical scaling laws for dataset size, compute budget, and inference requirements.
- Apply advanced methods for training, tuning, inference, and deployment to maximize performance.
- Analyze the challenges and opportunities of generative AI in business contexts, supported by insights from industry experts.
This intermediate-level course is ideal for developers with Python programming experience and foundational knowledge of machine learning concepts such as supervised and unsupervised learning, loss functions, and data splitting.
- A collection of practical labs demonstrating the implementation of LLMs for various tasks.
- Topics include:
- Fine-tuning LLMs
- Prompt engineering
- Text generation and summarization
- Evaluation of LLM outputs
- Comprehensive notes summarizing key concepts and methodologies discussed in the course.
- Topics covered:
- Transformer architecture
- Generative models: GPT, BERT, and beyond
- Applications of LLMs in real-world scenarios
- Ethical considerations in AI
- My official Coursera certificate of completion. View Certificate
- Hands-On Experience: Work directly with LLMs in real-world applications.
- Advanced Techniques: Learn fine-tuning, prompt engineering, and model evaluation.
- Expert Instruction: Content delivered by industry-leading professionals.
If you have questions or suggestions, feel free to reach out:
- Email: [email protected]
- LinkedIn: Lilia MAHDID