Deep Dive Into LLMs
Go beyond basic prompting by mastering transformer internals and fine-tuning techniques to build sophisticated, production-ready AI agents integrated directly into your engineering workflows. * **Architectural mastery** of Transformer blocks and attention mechanisms * **Fine-tuning expertise** using LoRA and QLoRA techniques * **Custom agent construction** with advanced reasoning and tool-use * **Open-source integration** into production software engineering workflows
5 sections ยท 20 lessons
Course outline
Training Pipeline
- Three Training Stages
- Internet Data Curation
- Tokenization Fundamentals
- Neural Network Training
- Base Models Explained
- Text Generation Process
Post-Training
- Supervised Fine-Tuning
- Conversation Tokenization
Limitations
- Hallucinations
- Tool Use Integration
- Computational Limits
- Tokenization Blind Spots
Reinforcement Learning
- Reinforcement Learning Basics
- RL in Math & Code
- Chain of Thought
- RLHF for Subjective Tasks
- RLHF Limitations
Practical Insights
- Mental Model of AI
- LLM Ecosystem
- Future Capabilities