BAKKOU, ADNANE, Badr Hirchoua, Mouad Banane, and Naoufal Er-raji, trans. “Structured Pruning of Small Language Models: An Empirical Study on GQA-Aware Attention and MLP Compression With LoRA Recovery”. International Journal of Advances in Soft Computing and its Applications 18, no. 3 (October 9, 2026): 113–139. Accessed October 10, 2026. https://ijasca.zuj.edu.jo/index.php/IJASCA/article/view/171.