# Lightweight Architecture

SAM2 model based on the HieraDet image encoder, focused on image feature extraction tasks.

Linknet is a PyTorch-implemented image segmentation model suitable for semantic segmentation tasks.

Chronos is a family of pretrained time series forecasting models based on language model architectures, trained by quantizing and scaling time series into token sequences.

Hiera is an efficient hierarchical vision Transformer model that excels in image and video tasks with fast runtime

Hiera is a hierarchical vision Transformer model that is fast, powerful, and concise, surpassing existing technologies in image and video tasks while being faster.

Hiera is a hierarchical vision Transformer model that is fast, powerful, and concise, surpassing state-of-the-art performance in a wide range of image and video tasks while significantly improving runtime speed.

Hiera is a hierarchical vision Transformer model that is fast, powerful, and concise, excelling in image and video tasks.

A randomly initialized model based on the Mistral architecture, suitable for end-to-end testing.

EfficientNetV2 is a highly efficient convolutional neural network architecture, specially optimized for training speed and parameter efficiency. The 61-channel version is a variant of this architecture.

LeViT-256 is an efficient vision model based on Transformer architecture, designed for fast inference and pretrained on the ImageNet-1k dataset.

Arabic pretrained version of ALBERT large model, trained on approximately 4.4 billion words of Arabic corpus

ReXNet-1.3x is an image classification model based on the ReXNet architecture, pretrained on the ImageNette dataset. The model reduces channel redundancy by improving the Squeeze-Excitation layers in residual blocks.

ReXNet-1.5x is a lightweight image classification model pretrained on the ImageNette dataset, utilizing the ReXNet architecture. It reduces channel redundancy by improving the Squeeze-Excitation layers within residual blocks.

Pre-trained CSP-Darknet-53 Mish architecture image classification model based on the ImageNette dataset