CODETIPS ACADEMY / FINE-TUNING METHODS

Fine-Tuning Methods

Build a Workshop Assistant with ten beginner-friendly articles and executed Python notebooks. Start with what fine-tuning means, then inspect each method through code, arithmetic, and diagrams.

GitHub publishing and linking guide · Execution report

1. 
   Part 1

   What Is Fine-Tuning? Teach an Existing Model a New Job

   Understand weights, training, and useful applications with a one-weight numerical experiment.

   Matching notebook
2. 
   Part 2

   Prepare the Data and Build a Baseline Before Training

   Create a labeled workshop dataset, keep paraphrases together, and learn what a baseline reveals.

   Matching notebook
3. 
   Part 3

   Full Fine-Tuning Versus a Frozen Encoder

   Adapt a pretrained miniature router and inspect exactly which parameters changed.

   Matching notebook
4. 
   Part 4

   Adapters, Bias-Only Updates, and Soft Prompts

   Learn the PEFT family by training a bottleneck adapter and inspecting bias-only updates.

   Matching notebook
5. 
   Part 5

   LoRA from Scratch: Two Small Matrices Instead of One Large Update

   Calculate a LoRA update by hand, train it, and prove that merging preserves predictions.

   Matching notebook
6. 
   Part 6

   Quantization and QLoRA: Understand the Memory Trade-Off

   Quantize a small matrix, measure reconstruction error, and train an update around a frozen quantized base.

   Matching notebook
7. 
   Part 7

   Supervised Fine-Tuning: Teach a Model the Desired Response

   Pretrain a tiny language model, mask prompt tokens, and teach a simple instruction-to-label format.

   Matching notebook
8. 
   Part 8

   Preference Tuning and DPO: Learn Which Answer Is Better

   Calculate the DPO objective and train a tiny response-choice policy against a frozen reference.

   Matching notebook
9. 
   Part 9

   Evaluate, Compare, and Save Your Fine-Tuned Model

   Compare five adaptation methods, inspect a confusion matrix, and verify a saved model reloads correctly.

   Matching notebook
10. 
    Part 10

    Use a Pretrained Model and Publish Your Notebooks on GitHub

    Move from teaching models to an optional LoRA training script, then connect each notebook to its website article.

    Matching notebook