Tongyi
Qwen

Qwen2 VL 72B Instruct

qwen/qwen2-vl-72b-instruct

Qwen2-VL is the latest iteration of multimodal large language models developed by the Qwen team at Alibaba Cloud. This advanced AI system represents a significant leap forward in the field of vision-language models, building upon its predecessor, Qwen-VL. Qwen2-VL boasts state-of-the-art capabilities in understanding images of various resolutions and aspect ratios, as well as the ability to comprehend videos exceeding 20 minutes in length. One of the most notable features of Qwen2-VL is its versatility as an agent capable of operating mobile devices, robots, and other systems based on visual input and text instructions. This makes it a powerful tool for a wide range of applications, from personal assistance to industrial automation. The model also offers robust multilingual support, enabling it to understand and process text in various languages within images, catering to a global user base.

Capability

Vision Support

00

Using Qwen2 VL 72B Instruct with Python API

Using Qwen2 VL 72B Instruct with OpenAI compatible API

import openai

client = openai.Client(
  api_key= '{your_api_key}',
  base_url="https://api.model.box/v1",
)
response = client.chat.completions.create(
model="qwen/qwen2-vl-72b-instruct",
messages: [
  {
    role: 'user',
    content:
      'introduce your self',
    },
  ]
)
print(response)