研究人员开发了CRePE，一种用于大型语言模型训练后剪枝的新方法，通过结合二维局部邻域上下文和自适应系数来提高效率。该方法在各种模型和稀疏度级别上都优于现有的剪枝技术。为了加速优化过程，他们还引入了PHO，一种基于代理的超参数优化方法，将搜索时间从几小时显著缩短到几分钟，并在不同模型上表现出强大的泛化能力。 AI
影响 降低了LLM部署的计算成本，可能加速其采用并实现更高效的模型使用。
排序理由 该集群包含一篇详细介绍模型剪枝新方法的论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.01544v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training. Amon…
Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training. Among existing methods, RIA introduces relative impo…