GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning

Autor: Ed-dib, Abdessalam, Datbayev, Zhanibek, Aboussalah, Amine Mohamed

Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between expressivity an

Externí odkaz: http://arxiv.org/abs/2412.09250

Semisupervised Nonnegative Matrix Factorization for learning the semantics.

Autor: Shen, Bin, Datbayev, Zhanibek, Makhambetov, Olzhas

Publikováno v: 6th International Conference on Soft Computing & Intelligent Systems & The 13th International Symposium on Advanced Intelligence Systems; 2012, p821-824, 4p