What is LoRA (Low-Rank Adaptation)?

Methods that adapt models by training a small subset of added parameters.

A fine-tuning technique that combines 4-bit weight quantization with LoRA adapters to reduce memory needs.

Continuing training on domain-specific data to adapt a pre-trained model to a specific task.

Fine-tuning a model on instruction-response pairs to improve task following.

A training method that fine-tunes models directly on preference pairs without needing a separate reward model.

A regularization method that softens hard labels to improve generalization.