AI engineering glossary · LLM training alignment
What is prefix tuning?
Prefix tuning: A parameter-efficient method that learns continuous vectors prepended to the attention keys and values at every layer while the model itself is frozen. Only these vectors are trained and stored for each task.
Prefix tuning: an example
20 learned prefix vectors per layer steer a frozen model to produce table-to-text summaries.
Related terms
More LLM training alignment terms
- Pretraining
- Process reward model
- Prompt tuning
- Proximal policy optimisation
- QLoRA
- Rank (LoRA)
- Reasoning model
- Reinforcement learning from AI feedback
Where you learn it
Prefix tuning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.