What is Fine-tuning?

Why does Fine-tuning matter?

Fine-tuning can adapt behavior, style, format, or task performance, but it is not a dependable replacement for retrieval when facts must stay current or traceable.

What is the common confusion about Fine-tuning?

Fine-tuning can influence encoded knowledge, but it does not simply append records to a searchable database inside the model.

Learn Fine-tuning in the course

Start with

• Fine-Tuning with LoRA & QLoRA

  Full fine-tuning a 7B model requires 56GB of VRAM. You don't have that. Neither do most companies. LoRA lets you fine-tune the same model in 6GB by training less than 1% of the parameters.

  Phase 11: LLM Engineering

Lessons that name Fine-tuning in a title or section

• Transfer Learning & Fine-Tuning

  Somebody else spent a million GPU hours teaching a network what edges, textures, and object parts look like. You should borrow those features before training your own.

  Phase 04: Computer Vision

• Stable Diffusion — Architecture & Fine-Tuning

  Stable Diffusion is a DDPM that runs in the latent space of a pretrained VAE, conditioned on text via cross-attention, sampled with a fast deterministic ODE solver, and steered by classifier-free…

  Phase 04: Computer Vision

• Whisper — Architecture & Fine-Tuning

  Whisper is a 30-second-window transformer encoder-decoder, trained on 680k hours of multilingual weakly-supervised audio-text pairs. One architecture, multiple tasks, robust across 99 languages.

  Phase 06: Speech & Audio

• Capstone 07 — End-to-End Fine-Tuning Pipeline (Data to SFT to DPO to Serve)

  An 8B model trained on your own data, DPO-aligned on your own preferences, quantized, speculative-decoded, and served at measurable $/1M tokens.

  Phase 19: Capstone Projects

• Capstone Lesson 38: Classifier Fine-Tuning by Head Swap

  Track B's first capstone. A pretrained language model is a stack of self-attention blocks ending in a token-prediction head. When you want spam vs ham, the head is wrong but the body is mostly right.

  Phase 19: Capstone Projects

• Capstone Lesson 39: Instruction Tuning by Supervised Fine-Tuning

  A pretrained base model can extend a sequence but cannot follow an instruction. Supervised fine-tuning is the smallest change that fixes this: feed the model paired examples of an instruction and a…

  Phase 19: Capstone Projects

• Vision-Language Models — The ViT-MLP-LLM Pattern

  A vision encoder converts an image into tokens. An MLP projector maps those tokens into the LLM's embedding space. A language model does the rest.

  Phase 04: Computer Vision

• Machine Translation

  Translation is the task that paid for NLP research for thirty years and keeps paying now. A model reads a sentence in one language and produces a sentence in another. Length varies. Word order varies.

  Phase 05: NLP: Foundations to Advanced

Taught in Phase 11: LLM Engineering.

Also covered in Phase 04: Computer Vision, Phase 05: NLP: Foundations to Advanced, Phase 06: Speech & Audio, Phase 18: Ethics, Safety & Alignment and Phase 19: Capstone Projects.

Related terms

• SFT (Supervised Fine-Tuning)Fine-tuning a pretrained model on paired inputs and desired responses so it learns the demonstrated behavior under the training…
• LoRA (Low-Rank Adaptation)A method that keeps base weights frozen and learns low-rank update matrices for selected layers.
• QLoRAA parameter-efficient fine-tuning method that keeps a pretrained base model frozen in a low-bit quantized representation while training…
• RAG (Retrieval-Augmented Generation)A system pattern that retrieves evidence relevant to a request and supplies selected content to a generative model before it answers or…
• Knowledge DistillationTraining a student model to reproduce selected behavior or output distributions from a more capable teacher, often alongside ordinary…
• Transfer LearningStarting from representations or parameters learned on one data distribution or objective and adapting them for another.

More terms in Math & training

• Activation Checkpointing
• Activation Function
• Adam (Optimizer)
• AdamW
• Autograd
• Backpropagation
• Batch Size
• Contrastive Learning
• Cross-Entropy
• Data Augmentation
• DPO (Direct Preference Optimization)
• Dropout
• Eigenvalue
• Epoch
• Gradient
• Gradient Accumulation
• Gradient Clipping
• Gradient Descent
• Hyperparameter
• JAX
• Knowledge Distillation
• Learning Rate
• Learning Rate Schedule
• LoRA (Low-Rank Adaptation)
• Loss Function
• Mixed Precision
• NaN (Not a Number)
• Normalization
• Optimizer
• Overfitting
• QLoRA
• ReLU
• RLHF (Reinforcement Learning from Human Feedback)
• SFT (Supervised Fine-Tuning)
• Softmax
• Stochastic Gradient Descent (SGD)
• Transfer Learning
• Underfitting
• Warmup
• Weight
• Weight Decay

Open the Math & training list in the glossary