首页/数据集/Performance comparison of different lightweighting models.

Performance comparison of different lightweighting models.

Figshare2025-07-28 更新2026-04-28 收录

模型轻量化

模型压缩

数据链接：

https://figshare.com/articles/dataset/Performance_comparison_of_different_lightweighting_models_/29659050 数据链接链接失效反馈

官方服务：

资源简介：

Performance comparison of different lightweighting models.

应用场景：

创建时间：

2025-07-28

相关数据集

neuralmagic/LLM_compression_calibration

大语言模型

模型压缩

该数据集是Neural Magic用于大型语言模型（LLMs）一次性压缩校准的默认校准数据集。当前版本的数据集从garage-bAInd/Open-Platypus中编译而来，包含10,000个样本。数据集包含两个字段：text用于当聊天模板不可用时的文本输入，messages包含用户和助手角色的字典条目，用于与聊天模板一起使用。

Hugging Face2024-06-27 更新420

Comparison of trainable parameters and model sizes of ViT variants and the proposed CNN-ViT model.

计算机视觉模型

模型压缩

Comparison of trainable parameters and model sizes of ViT variants and the proposed CNN-ViT model.

NIAID Data Ecosystem10

The Top-1 accuracy of the student network ResNet20 using different fusion methods where the teacher is ResNet56 on CIFAR-100.

知识蒸馏

模型轻量化

The Top-1 accuracy of the student network ResNet20 using different fusion methods where the teacher is ResNet56 on CIFAR-100.

NIAID Data Ecosystem10

Sparsity of each model (Ratio of zero weights between the hidden layer and the output layer).

神经网络稀疏性

模型压缩

Sparsity of each model (Ratio of zero weights between the hidden layer and the output layer).

NIAID Data Ecosystem20

CXR dataset for model generalization.

医学影像分类

模型轻量化

Deep Neural Networks (DNN) have achieved state-of-the-art performance in medical image classification and are increasingly being used for disease diagnosis. However, these models are quite complex and

Figshare2025-03-20 更新10