LLM Engineering & Generative AI · LLM Engineering & Generative AI

LLM Finetuning

This track covers the practical skills for adapting pretrained large language models to your own data. You'll learn data preparation, parameter-efficient methods like LoRA and QLoRA, training loops with Hugging Face Transformers, and evaluation strategies. Ideal for ML engineers and developers wanting to customize LLMs for specific tasks, it ends with deploying a fine-tuned model responsibly.

Start tutorial

Sponsored

Lesson outline

  1. 25
    Save & Load a Finetuned Checkpoint

    Learn how to save and load a finetuned checkpoint for your LLM — a practical step-by-step lesson in the LLM Finetuning track. Covers the core concept, hands-on walkthrough, and troubleshooting tips to keep your work safe.

  2. 26
    8x A100 GPU Setup

    Set up an 8x A100 GPU training environment for LLM finetuning. Step-by-step guide covering hardware, software, and configuration.

  3. 27
    Load Pretrained Models from Hugging Face Hub

    Learn how to load pretrained models from the Hugging Face Hub, a key first step in LLM fine-tuning. This lesson covers the AutoModel and AutoTokenizer APIs, practical code examples, and common pitfalls. By the end, you'll be ready to start customizing these models for your own tasks.

  4. 28
    Apply LoRA Adapters

    Learn to apply LoRA adapters to a base model in this hands-on LLM Finetuning lesson. Understand the core concept, follow a step-by-step walkthrough, troubleshoot common issues, and know what to study next.

  5. 29
    Choosing LoRA Rank and Alpha

    Choose LoRA rank and alpha hyperparameters for your LLM finetuning in this step-by-step tutorial. Learn the core mental model, hands-on walkthrough, comparisons, troubleshooting, and what to study next.

  6. 30
    Merge LoRA Weights

    Learn to merge LoRA adapter weights into the base model for deployment. Step-by-step guide with troubleshooting.

  7. 31
    Run Your First QLoRA Script

    Write and run your first QLoRA training script with hands-on steps, troubleshooting tips, and what to learn next.

  8. 32
    Optimize QLoRA with 4-Bit Quantization

    Learn to optimize QLoRA with 4-bit quantization in this hands-on LLM finetuning tutorial. Step-by-step techniques, troubleshooting, and next steps for efficient model adaptation.

  9. 33
    Use PEFT for Fine-Tuning

    Learn to use PEFT for parameter-efficient fine-tuning in this step-by-step LLM Finetuning tutorial. Master LoRA and QLoRA.

  10. 34
    Build a Custom Dataset Class

    Learn to build a custom dataset class for finetuning LLMs. This lesson covers the why, how, and practical implementation steps.

  11. 35
    Split Data: Train & Validation

    Learn how to split your dataset into training and validation sets for LLM fine-tuning. This hands-on tutorial covers the why, the how, and common pitfalls, with a practical walkthrough to get you started.

  12. 36
    Causal LM Data Collator

    Build a data collator for causal language model training and understand how it shapes your batches for the next-token prediction task.

    LLM Finetuning — step-by-step tutorials

    What you will find here

    This track walks through llm finetuning in order — each lesson is server-rendered HTML you can read without JavaScript. Follow the outline, then practice in the browser IDE when a lesson links to runnable code.

    Tutorials vs quizzes and code samples

    Tutorials teach in sequence. For quick checks use quizzes. For copy-paste snippets see code samples. For deeper reading browse articles.