What is ModelSmith?
ModelSmith, an open source project toolkit, is designed to optimize models for deployment across a wide array of devices and platforms. This ensures that Deep Neural Networks operate more efficiently, becoming faster, smaller, and more energy efficient.
Furthermore, ModelSmith specializes in the compression of machine learning models. This process is crucial for facilitating the deployment of large machine learning models on diverse devices and platforms, thereby maintaining satisfactory performance standards.
Additionally, ModelSmith plays a pivotal role in reconciling the supply and demand disparities in AI computing. It achieves this by tailoring models to meet the requirements of various real- world applications, effectively bridging the gap between theoretical advancements and practical utility in the field of artificial intelligence.
Why ModelSmith?
ModelSmith offers innovative solutions tailored to meet the diverse needs of machine learning practitioners. Whether you are working with vision models, natural language models, or multi-modal models, ModelSmith has you covered. Its arsenal of model compression and machine unlearning algorithms ensures that your models are optimized for real-world deployment.
What sets ModelSmith apart is its user-centric approach. With a user-friendly interface and comprehensive guidance. ModelSmith empowers users of all expertise levels to select the most suitable algorithms for their specific requirements. Whether you are a seasoned AI veteran or just starting your journey, ModelSmith makes model optimization accessible to everyone.
Moreover, ModelSmith leverages a wide array of technologies, including quantization, pruning, and machine unlearning, to deliver versatile solutions. This versatility allows ModelSmith to adapt to the unique needs of each application, effectively reconciling the supply and demand disparities in AI computing.
Publication
- Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling
(NeurIPS 2023) Haotao Wang, Ziyu Jiang, Yuning You, Yan Han, Gaowen Liu, Jayanth Srinivasa, Ramana Kompella, Zhangyang Wang
- Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
(NeurIPS 2023) Yihua Zhang, Yimeng Zhang, Aochuan Chen, Jiancheng Liu, Gaowen Liu, Mingyi Hong, Shiyu Chang, Sijia Liu
- Model sparsity can simplify machine unlearning
(NeurIPS 2023) Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
- Adaptive Deep Neural Network Inference Optimization with EENet
(WACV 2024) Fatih Ilhan, Ka-Ho Chow, Sihao Hu, Tiansheng Huang, Selim Tekin, Wenqi Wei, Yanzhao Wu, Myungjin Lee, Ramana Kompella, Hugo Latapie, Gaowen Liu, Ling Liu
- Causal-dfq: Causality guided data-free network quantization
(ICCV 2023) Yuzhang Shang, Bingxin Xu, Gaowen Liu, Ramana Rao Kompella, Yan Yan
- Network specialization via feature-level knowledge distillation
(CVPR 2023 WS) Gaowen Liu, Yuzhang Shang, Yuguang Yao, Ramana Kompella
- Efficient Multitask Dense Predictor via Binarization
(CVPR 2024) Yuzhang Shang, Dan Xu, Gaowen Liu, Ramana Rao Kompella, Yan Yan
- Enhancing Post-training Quantization Calibration through Contrastive Learning
(CVPR 2024) Yuzhang Shang, Gaowen Liu, Ramana Rao Kompella, Yan Yan
- MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
(CVPR 2024) Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci
Getting Started
This document is a good starting point. Users can set it up in a MacOS or Linux (e.g., Ubuntu 20.04). For other OS platforms, a Linux VM can be used.
Support
We welcome feedback, questions, and issue reports.
Contributors
Illinois Institute of Technology CVM Lab
Michigan State University OPTML Group