← 模型广场

Qwen: Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct

图像理解JSON流式

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

价格

输入

$0.25 / 1M

输出

$0.75 / 1M

参数

上下文

131,072 tokens

输入模态

text, image

输出模态

text

知识截止:2024-06-30

发布:2025-02

支持参数

frequency_penaltylogit_biasmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p

开放权重 · HuggingFace

381,678 月下载
623 收藏
other image-text-to-text
在 HuggingFace 查看 →