id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
ajm-7891	Shakti , Shivay; Hajong , Drishti; Dubey , Priyanshi	Optimizing Large Language Models for Resource-Constrained Environments: A Parameter-Efficient Approach Using QLoRA and Prompt Tuning	2025	16	.pdf	application/pdf	4999	264	38	Dettmers et al. (2023) showed that QLoRA achieves an 85% reduction in memory requirements compared to traditional fine-tuning methods, without compromising model accuracy. The effect of varying prompt sizes on model accuracy is presented in FIGURE 4.	cache/ajm-7891.pdf	txt/ajm-7891.txt