首页
教程
IT编程
国外技术
登录
标签
Quantization
A Comprehensive Evaluation of Quantization Strategies for Large Language Models
本文是LLM系列文章,针对《A Comprehensive Evaluation of Quantization Strategies for Large Language Models》的翻译。大型语言模型量化策略的综合评价 摘要 1
Quantization
evaluation
Comprehensive
strategies
Models
admin
6月前
72
0
深度学习论文: Data-Free Quantization Through Weight Equalization and Bias Correction及其PyTorch实现
Data-Free Quantization Through Weight Equalization and Bias Correction PDF:https:openaccess.thecvfcontent_ICCV_2019p
深度
论文
Free
DATA
Quantization
admin
7月前
86
0
[Arxiv 2024] PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs
ContentsIntroductionMethodExperimentsReferencesIntroduction 作者提出 PrefixQuant,基于 QuaRot,通过在 WA 量化时
static
Quantization
PrefixQuant
arxiv
Outliers
admin
7月前
64
0