Training & Fine-tuning
RAG vs Fine-Tuning: Which One Should You Use for Your LLM?
RAG or fine-tuning? Use a simple decision framework to pick the right approach for knowledge, style and cost, with trade-offs and a worked LoRA example.
Read the guide
Guides
Deep dives between the course and the docs: each guide explains one decision you will actually have to make, with the trade-offs spelled out.
Training & Fine-tuning
Gradient Checkpointing Explained: Trade Compute for Memory
Learn how gradient checkpointing cuts training memory by recomputing activations during backprop, and when the extra compute is worth it for large models.
Read the guide
Training & Fine-tuning
How Much Data Do You Need to Fine-Tune an LLM?
Learn how many examples you really need to fine-tune an LLM with LoRA, from a few hundred to tens of thousands, and what factors change the answer.
Read the guide
Training & Fine-tuning
Fine-Tune an LLM for Free on Google Colab
Learn how to fine-tune an LLM for free on Google Colab using LoRA and QLoRA, from setup to training and evaluation, step by step.
Read the guide
Training & Fine-tuning
How Much GPU Memory to Fine-Tune Llama 3 8B
Estimate the GPU VRAM needed to fine-tune Llama 3 8B with LoRA: weights, gradients, optimizer states, activations, and practical batch-size tradeoffs.
Read the guide
Training & Fine-tuning
LoRA vs QLoRA: Efficient Fine-Tuning Explained
Compare LoRA and QLoRA for parameter-efficient fine-tuning: how each works, memory trade-offs, and when to choose one over the other.
Read the guide
Training & Fine-tuning
RAG vs Fine-Tuning: How to Choose (With Cost Math)
Compare RAG and fine-tuning on cost, latency, and accuracy. Work through the actual math to pick the right approach for your LLM use case.
Read the guide