LLM Fundamentals
Master the underlying architecture and mechanisms of modern AI to bridge the gap between using tools and building robust, production-ready applications for your new career. * **Core architecture** behind Transformers and attention mechanisms * **Training pipelines** including pre-training and supervised fine-tuning * **Model evaluation** using technical benchmarks and performance metrics * **Deployment strategies** for integrating models into production environments
10 sections ยท 28 lessons
Course outline
Foundational Concepts
- Text to Numbers
- Vectors: The DNA of AI Language
- Layered Processing
- Tokenization
- Embeddings
Sequential Processing Problems
- Sequential Limitations
Transformer Architecture
- Parallel Processing
- Query-Key-Value
- Attention Weights
Self-Attention Mechanics
- Self-Attention
- Causal Masking
- Multi-Head Attention
Model Architectures
- Architecture Types
- Model Scale
Pre-Training Process
- Pre-Training
- Next-Word Prediction
Fine-Tuning and Alignment
- Fine-Tuning: Specializing Pre-Trained Models
- RLHF Overview
- RLHF Stages
Text Generation
- Autoregressive Generation
- Softmax Transformation
- Temperature: Controlling Output Randomness
- Sampling Strategies
Generation Control
- Creativity vs Precision
Model Limitations
- Hallucinations
- Mitigating Hallucinations
- Context Windows
- Context Management