热点
"二值化" 相关文章
BEExformer: A Fast Inferencing Binarized Transformer with Early Exits
cs.AI updates on arXiv.org 2025-07-15T04:24:20.000000Z
突破瓶颈！北航ETH等首次将扩散模型完全量化至1bit，28倍存储节省+52.7倍效率提升
量子位 2025-01-12T16:08:27.000000Z
突破瓶颈！北航ETH等首次将扩散模型完全量化至1bit，28倍存储节省+52.7倍效率提升
智源社区 2025-01-12T05:07:20.000000Z
Researchers from MBZUAI and CMU Introduce Bi-Mamba: A Scalable and Efficient 1-bit Mamba Architecture Designed for Large Language Models in Multiple Sizes (780M, 1.3B, and 2.7B Parameters)
MarkTechPost@AI 2024-11-23T18:34:58.000000Z
FBI-LLM (Fully BInarized Large Language Model): An AI Framework Using Autoregressive Distillation for 1-bit Weight Binarization of LLMs from Scratch
MarkTechPost@AI 2024-07-14T07:16:16.000000Z