방법 비교

	QLoRA	맘바 (상태 공간 모델)
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2023	2023
창시자	Tim Dettmers	Albert Gu
유형	Training methodology	Neural network architecture
원전	Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314.	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.
별칭	QLoRA, Quantized LoRA	Mamba, State space models, Selective state space
관련	4	4
요약	QLoRA is an efficient fine-tuning method introduced by Dettmers et al. in 2023 that enables fine-tuning large language models using quantization and low-rank adaptation. By combining 4-bit quantization with LoRA, QLoRA reduces memory requirements by 75%, enabling fine-tuning of 65B-parameter models on single GPUs.	Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power.