Fine-Tuning
The process of taking a pre-trained model and further training it on a smaller, domain-specific dataset to specialize its behavior for a particular task or domain. Fine-tuning adjusts the model's weights to improve performance on the target task.
Why It Matters
Fine-tuning lets organizations customize powerful base models for their specific needs — custom terminology, tone, formats, and domain expertise — without training from scratch.
Example
A hospital fine-tuning a general language model on medical literature and clinical notes so it better understands medical terminology and can assist with clinical documentation.
Think of it like...
Like a general practitioner doctor going through a residency to become a specialist — they already have broad medical knowledge and are now deepening expertise in one area.
Related Terms
Pre-training
The initial phase of training a model on a large, general-purpose dataset before specializing it for specific tasks. Pre-training gives the model broad knowledge and capabilities.
LoRA
Low-Rank Adaptation — a parameter-efficient fine-tuning technique that freezes the original model weights and adds small trainable matrices to each layer. It dramatically reduces the compute and memory needed for fine-tuning.
QLoRA
Quantized Low-Rank Adaptation — combines LoRA with quantization to further reduce memory requirements for fine-tuning. It quantizes the base model to 4-bit precision while training LoRA adapters in higher precision.
Transfer Learning
A technique where a model trained on one task is repurposed as the starting point for a model on a different but related task. Instead of training from scratch, you leverage knowledge the model has already acquired.
Training Data
The dataset used to teach a machine learning model. It contains examples (and often labels) that the model learns patterns from during the training process. The quality and quantity of training data directly impact model performance.