2024/10/01 by Muñoz, Juan Pablo, Jinjie Yuan, Yuan, Jinjie +2 · 3 citations
Earth and Planetary Sciences · Engineering · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Drilling and Well Engineering #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reservoir Engineering and Simulation Methods #Seismic Imaging and Inversion Techniques
paper · pdf · doi:10.48550/arxiv.2410.03750
openalex publication_date 2024/10/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Large pre-trained models (LPMs), such as large language models, have become ubiquitous and are employed in many applications. These models are often adapted to a desired domain or downstream task through a fine-tuning stage. This paper proposes SQFT, an end-to-end solution for low-precision sparse parameter-efficient fine-tuning of LPMs, allowing for effective model manipulation in resource-constrained environments. Additionally, an innovative strategy enables the merging of sparse weights with low-rank adapters without losing sparsity and accuracy, overcoming the limitations of previous approaches. SQFT also addresses the challenge of having quantized weights and adapters with different numerical precisions, enabling merging in the desired numerical format without sacrificing accuracy. Multiple adaptation scenarios, models, and comprehensive sparsity levels demonstrate the effectiveness of SQFT. Models and code are available at https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.