Jiahang Shao

Peking University

No. 38 Xueyuan Road

Haidian District

Beijing, 100871

China

SCHOLARLY PAPERS

1

DOWNLOADS

207

TOTAL CITATIONS

0

Scholarly Papers (1)

1.

Pt-Bitnet: 1-Bit Large Language Model with Post-Training Quantization

Number of pages: 10 Posted: 14 Oct 2024
affiliation not provided to SSRN, Peking University, Peking University, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN and affiliation not provided to SSRN
Downloads 207 (298,658)

Abstract:

Loading...

Large Language ModelsTernary QuantizationPost-Training QuantizationEfficient Inference