Language-model training and adaptation · MLD-0447
Full fine-tuning
Updating all or nearly all model parameters during adaptation.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Specialize an entire model on domain data.
Original caveat
It usually needs more trainable-state memory than adapter methods.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Evaluation.
Tags: DL · SLM · LLM · NLP.
Aliases: Full-parameter fine-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 ↗