# Real-time Inference

LeYOLO is an object detection model based on the YOLO architecture, offering four scales: nano, small, medium, and large

Depth Anything V2 is currently the most powerful Monocular Depth Estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

This model is released under the Apache-2.0 license, with specific details currently unknown.

This model is released under the MIT License, and further details need to be supplemented.

YOLOS is an object detection model based on the Transformer architecture, designed for efficient visual task processing.

YOLOS-small is a small object detection model based on the Transformer architecture, designed for efficient visual tasks.

A versatile large language model capable of handling various natural language tasks

A versatile language model based on Transformer architecture, supporting tasks such as text generation, Q&A, and code completion

A versatile large language model capable of handling various natural language tasks

This is a general model description, a brief introduction not exceeding 150 words.