The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Jul. 29, 2025
Filed:
Dec. 01, 2022
Samsung Electronics Co., Ltd., Suwon-si, KR;
Qian Lou, Oviedo, FL (US);
Yen-Chang Hsu, Fremont, CA (US);
Burak Uzkent, Mountain View, CA (US);
Ting Hua, Cupertino, CA (US);
Yilin Shen, San Jose, CA (US);
Hongxia Jin, San Jose, CA (US);
Samsung Electronics Co., Ltd., Suwon-si, KR;
Abstract
A method includes obtaining, using a first electronic device, a weight matrix associated with a trained transformer model. The method also includes factorizing the weight matrix into a dictionary weight matrix and an intermediate matrix. The method further includes pruning the intermediate matrix to generate a sparse intermediate matrix. The method also includes fine-tuning the sparse intermediate matrix based on a training dataset to generate a fine-tuned sparse intermediate matrix. The method further includes determining an index matrix and a coefficient matrix based on the fine-tuned sparse intermediate matrix. In addition, the method includes deploying the dictionary weight matrix, the index matrix, and the coefficient matrix to a second electronic device without deploying the weight matrix to the second electronic device. A number of parameters in the dictionary weight matrix, the index matrix, and the coefficient matrix is smaller than a number of parameters in the weight matrix.