Results for "low-rank adaptation"

PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.

Randomly zeroing activations during training to reduce co-adaptation and overfitting.

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

Measure of consistency across labelers; low agreement indicates ambiguous tasks or poor guidelines.

Low-latency prediction per request.

Ultra-low-latency algorithmic trading.

Number of linearly independent rows or columns.