Learn AI / Term Explorer /Training and Model Adaptation
Training and Model Adaptation
The stages between a raw model and a usable one, and the several different things people mean by "training it on our data".
Starter
Fine-tuning
Updating a pre-trained model's parameters with additional examples to improve performance on a narrower task, style or domain.
Knowledge cutoff
The approximate point up to which a model’s training-derived background is expected to be current, while newer events and facts may be absent unless added another way.
Model version
A particular identified state of a model or model-backed system, with documented changes, capabilities and checks for use.
Intermediate
Alignment
Making an AI system's behaviour better match intended goals or preferences, often through methods applied after broad training.
Checkpoint
A saved copy of a model’s state at a particular point in training or adaptation, so work can be resumed, compared or released later.
In-context learning
A model uses examples and instructions placed in the current prompt to imitate a pattern for that one interaction, without changing its stored parameters.
Pretraining
A large-scale training stage where a model learns reusable patterns from data, producing a general-purpose starting point that later steps can adapt for specific tasks.
Reinforcement learning from human feedback
A method for adjusting a model so its outputs better match human preferences by learning from ranked examples and reward signals.
Zero-shot, one-shot and few-shot
These labels describe how many task examples a model gets in the prompt before it tries a new input: none, one, or a small handful.
Deeper
Distillation
Distillation trains a student model to imitate a teacher model’s outputs or other signals; the student is often smaller.
Instruction tuning
A post-pretraining adaptation step that teaches a general language model to respond to prompts in the requested format, style and task pattern.
LoRA
A method for adapting a large model by training a small set of added weights instead of changing most of the original model.
Parameter-efficient fine-tuning
A way to adapt a large model to a new task by training only a small set of added or selected weights instead of updating the whole model.
Preference learning
A method for adjusting a model so it more often produces outputs people rank as better, safer or more useful than alternatives.
Pruning
Pruning removes less useful connections or parameters to reduce model size or runtime while trying to keep nearly the same performance.
Quantisation
A method for storing and running a model with lower-precision numbers so it uses less memory and often runs faster, with some possible loss in accuracy.
Supervised fine-tuning
A pretrained model is further adapted by showing it input–output examples so its parameters better reproduce the target outputs for a chosen task or style.