qwen-turbo-latest.description

qwen-plus-latest.description

qwen-max-latest.description

Qwen is a large-scale language model that supports long text contexts and dialogue capabilities based on long documents and multiple documents.

Qwen is a large-scale visual language model enhanced version. It significantly improves detail recognition and text recognition capabilities, supporting images with resolutions over one million pixels and any aspect ratio.

Qwen is a large-scale visual language model. Compared to the enhanced version, it further improves visual reasoning and instruction-following capabilities, providing higher levels of visual perception and cognition.

qwen-math-turbo-latest.description

qwen-math-plus-latest.description

qwen-coder-turbo-latest.description

qwen2.5-7b-instruct.description

qwen2.5-14b-instruct.description

qwen2.5-32b-instruct.description

qwen2.5-72b-instruct.description

qwen2.5-math-1.5b-instruct.description

qwen2.5-math-7b-instruct.description

qwen2.5-math-72b-instruct.description

qwen2.5-coder-1.5b-instruct.description

qwen2.5-coder-7b-instruct.description

Initialized with the Qwen-7B language model, this pre-trained model adds an image model with an input resolution of 448.

Qwen VL supports flexible interaction methods, including multi-image, multi-turn Q&A, and creative capabilities.