FineTuningCategory
Enums · AiDotNet.Interfaces
Categories of fine-tuning methods.
For Beginners
These categories group fine-tuning methods by how they learn. Some learn from labeled data, others from preferences, and some from reward signals.
Fields
| Field | Summary |
|---|---|
FineTuningCategory Adversarial |
Adversarial methods that use game-theoretic approaches. |
FineTuningCategory Constitutional |
Constitutional AI methods that use principles for self-improvement. |
FineTuningCategory Contrastive |
Contrastive methods that learn from positive/negative examples. |
FineTuningCategory DirectPreference |
Direct Preference Optimization - learns directly from preference pairs. |
FineTuningCategory KnowledgeDistillation |
Knowledge distillation - transfer knowledge from teacher to student. |
FineTuningCategory OddsRatioPreference |
Odds/Ratio-based methods that combine SFT and preference learning. |
FineTuningCategory RankingBased |
Ranking-based methods that learn from response rankings. |
FineTuningCategory ReinforcementLearning |
Reinforcement Learning - learns from reward signals. |
FineTuningCategory SelfPlay |
Self-play methods where the model learns from itself. |
FineTuningCategory SupervisedFineTuning |
Supervised Fine-Tuning - learns from labeled input-output pairs. |
int value__ |