https://openreview.net/forum?id=z83rodY0Pw&referrer=%5Bthe%20profile%20of%20Samir%20Khaki%5D(%2Fprofile%3Fid%3D~Samir_Khaki1)
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity | OpenReview
Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of...
llm fine tuningacceleratingcontextualsparsityopenreview