← All courses
AI
LLM Fine Tuning Tutorial
LLM Fine Tuning Tutorial
4.7 (975)12,975 learners20 lessons1h 38m
Curriculum
Topic
- what is llm fine-tuning and why it matters3:55
- Pretraining vs Fine-tuning vs Prompt Engineering — Understanding the Differences4:00
- Fine-Tuning vs. RAG: When to Use Which?4:07
- Types of Fine-Tuning: Full, Partial, and Parameter-Efficient Explained4:19
- Understanding Training Data: What Makes a Good Fine-Tuning Dataset6:57
- Preparing and Formatting Instruction Datasets: Step by Step5:16
- Why Data Quality Beats Data Quantity in Fine-Tuning5:22
- The LLM Training Pipeline Explained End-to-End5:33
- Understanding Tokenization: How a Model Reads Your Data3:55
- Key Hyperparameters Explained: Learning Rate, Epochs, and Batch Size4:09
- Introduction to Parameter-Efficient Fine-Tuning (PEFT): Why Full Fine-Tuning Is Often Overkill4:06
- Understanding LoRA: Low-Rank Adaptation Explained Simply5:55
- QLoRA: Fine-Tuning Large Models on a Single GPU4:57
- Model Quantization Basics: INT8, 4-Bit, and BitsAndBytes5:50
- Supervised Fine-Tuning (SFT) with the Hugging Face Ecosystem4:17
- Introduction to Model Alignment: RLHF Explained Simply5:26
- Direct Preference Optimization (DPO): The Simpler Alternative to RLHF5:13
- Evaluating a Fine-Tuned Model: Benchmarks and LLM-as-Judge4:02
- Understanding Catastrophic Forgetting and How to Avoid It5:19
- Deploying Your Fine-Tuned Model: Adapters, Serving, and Inference5:34