Language-model training and adaptation · MLD-1133
Soft prompt
Trainable continuous vectors supplied as a prompt-like input.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Represent task instructions with learned embeddings.
Original caveat
They need not correspond to readable vocabulary tokens.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Evaluation.
Tags: DL · SLM · LLM · NLP.
Aliases: Virtual prompt tokens.
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 ↗