Category: LLM

This category contains 12 pages.

• Context Windows Explained
• Fine-tuning vs RAG vs Prompting
• How Transformers Work
• Mixture of Experts (MoE)
• Multimodal Models
• Reasoning Models and Test-Time Compute
• Reinforcement Learning from Human Feedback (RLHF)
• Temperature and Sampling Explained
• The Attention Mechanism
• Tokenization Explained
• What Are Embeddings
• Why LLMs Hallucinate