ContactSign in

Qwen2.5 VL AWQ 7B is a vision-language model that supports 7 billion parameters, offering advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.

Model details

CategoryDetails
Model NameQwen2.5 VL
VersionAWQ 7B
Model CategoryVLM
Size7B params
HuggingFace ModelQwen/Qwen2.5-VL-7B-Instruct-AWQ
OpenAI Compatible endpointChat API Overview
LicenseApache 2.0

Capabilities

FeatureDetails
Tool Calling✅
Context Length32k tokens
Supports LoRA✅
Input dataText + Image

Usage

Basic chat completion

This is a basic chat completion example using this model:

const modelResponse = await Azion.AI.run("qwen-qwen25-vl-7b-instruct-awq", {
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Name the european capitals"
    }
  ]
})

Tool Calling Example

const modelResponse = await Azion.AI.run("qwen-qwen25-vl-7b-instruct-awq", {
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant with access to tools."
    },
    {
      "role": "user",
      "content": "What is the weather in London?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state"
            }
          },
          "required": ["location"]
        }
      }
    }
  ]
})

Multimodal (text + image) example

const modelResponse = await Azion.AI.run("qwen-qwen25-vl-7b-instruct-awq", {
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ]
})

The response will be similar to the one in the Basic Chat Completion example.