Language-model training and adaptation · MLD-0959
Prompt tuning
Learning continuous prompt embeddings while freezing most or all model weights.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Adapt a model with trainable virtual tokens.
Original caveat
Different from manually writing a better text prompt.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Evaluation.
Tags: DL · SLM · LLM · NLP.
Aliases: Soft-prompt tuning.
Related concepts
Concepts linking here
Original references
- Transformers glossary ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- TRL: supervised fine-tuning ↗ · Reference link
- TRL documentation ↗ · Consulted
- Original reference URL ↗