Large Language Model

Fundamentals

• Generative Model - Autoregressive and diffusion architectures
• Patterns - Scaling law, emergent ability, hallucination

Training

• Pre-Training - Pre-trained models
• Fine-Tuning - SFT, instruction-tuning, LoRA
• Reinforcement Learning - PPO, GRPO, agentic RL

Inference

• Reasoning - Chain-of-thought and inference acceleration
• Evaluation - Accuracy, efficiency, and quality metrics

Applications

• Retrieval-Augmented Generation - Retrieval-augmented generation patterns

Resources

• Toolchain - Tools and frameworks