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. 37
    Fine-Tune NER Models

    Learn to fine-tune a transformer model for named entity recognition. This hands-on lesson covers data prep, tokenization, training with Hugging Face, and evaluation. Ideal for developers who want to customize NER systems.

  2. 38
    Text Classification Fine-Tuning

    Learn to fine-tune for text classification tasks with this concise LLM Finetuning tutorial. Step-by-step guidance, hands-on exercise, and troubleshooting tips.

  3. 39
    Fine-tune on SQuAD for Q&A

    Fine-tune for question answering on SQuAD — LLM Finetuning tutorial, lesson 39.

  4. 40
    Fine-tune LLM with ROUGE

    Fine-tune for summarization with ROUGE — LLM Finetuning. Learn practical steps to evaluate and improve your model's summarization quality in this hand-on lesson.

  5. 41
    Trainer API Training Loop

    Implement a training loop with Trainer API — LLM Finetuning.

  6. 42
    Use SFTTrainer for Supervised Instruction Tuning

    Learn to fine-tune LLMs with SFTTrainer for supervised instruction tuning. This tutorial covers setup, training, and evaluation.

  7. 43
    PPO for Preference Alignment

    Apply RLHF with PPO for preference alignment: learn how to fine-tune LLMs with reinforcement learning from human feedback.

  8. 44
    Add DPO to Align With Human Feedback

    Learn to add DPO to align your fine-tuned LLM with human feedback. Covers DPO concepts, practical implementation, and integration into your training pipeline.

  9. 45
    Balance Multiple Tasks with Multi-Task Finetuning

    Balance multiple tasks with multi-task finetuning — LLM Finetuning.

  10. 46
    Test Cross-Lingual Transfer

    Learn how to test cross-lingual transfer with a multilingual model. This lesson from the PythonSkillset LLM Finetuning track covers practical steps, troubleshooting, and what to study next.

  11. 47
    Inspect Adapter Weights

    Learn to inspect adapter weights for quality issues in LLM finetuning with LoRA/QLoRA. Step-by-step walkthrough, troubleshooting, and next steps.

  12. 48
    Debug NaN Loss in QLoRA

    Debug NaN loss during QLoRA training in this practical LLM Finetuning lesson. Learn to identify causes like unstable learning rates, mixed precision issues, and data problems, then apply step-by-step fixes to stabilize your training runs.

    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.