Tag: parameter efficiency
Browse our exclusive articles!
LARS: Memory-Efficient Fine-Tuning for On-Device LLMs
Discover how LARS reduces memory use in fine-tuning large language models on devices with limited resources, boosting efficiency without performance loss.
Efficient Multitask Transfer Learning for Clinical NLP
Discover a parameter-efficient multitask prompt distillation method improving clinical NLP with minimal trainable parameters and superior performance.
TalkLoRA: Efficient Communication in Low-Rank Adaptation for LLMs
Discover TalkLoRA, a communication-aware low-rank adaptation method that boosts efficiency and stability in large language model fine-tuning.
Tucker Attention: Efficient Generalized Approximate Mechanism
Discover Tucker Attention, a parameter-efficient generalization of approximate attention methods, enhancing performance in LLMs and vision transformers.