All Models
Qwen2.5-72B-Instruct
Qwen2.5-72B-Instruct is a flagship 72.7-billion parameter, open-weight model engineered for high-stakes AI production, advanced reasoning, and complex conversational tasks. Optimised with an 80-layer architecture using Grouped Query Attention (GQA), it delivers exceptional performance in coding, mathematics, and structured data tasks like JSON and table processing.
by @AIOZAI
Miro Thinker
MiroThinker is an open-source research agent that advances tool-augmented reasoning through model, context, and interactive scaling. It achieves state-of-the-art performance among open-source agents by enabling up to 600 tool calls per task within a 256K context window, demonstrating that interaction depth is a critical dimension for building next-generation research agents alongside model size and context length.
by @draven-2890
Collections
Image-to-Text
The Image-to-Text task is an important task in the field of natural language processing and computer vision. Its purpose is to convert information within an image into readable and understandable text.
Object Detection
The Object Detection task is an important task in the fields of computer vision and artificial intelligence. Its main objective is to detect and determine the position of objects within images or videos.
Image to Image
Image-to-Image is an important task in the field of image processing, where we convert images from one format or data type to another.
Housing Prices Challenge
House price prediction based on related factors such as house area, number of bedrooms, etc.
by @aiozai_mod
Face Anti-Spoofing Challenge
The Face Anti-spoofing Challenge aims to develop robust and accurate models that can distinguish between real human faces and various types of spoofing attempts.
by @aiozai_mod