nomagick/qwen-vl-chat:e48b4267 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

nomagick /qwen-vl-chat:e48b4267

Input

prompt

string

Shift + Return to add a new line

<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Given this image: <img>image1</img>, point out where the dog is<|im_end|>
<|im_start|>assistant
<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Given this image: <img>image1</img>, point out where the dog is<|im_end|>
<|im_start|>assistant

Prompt for completion, in chatml format

image1

file

Preview

Optional image you may use in your prompt known as image1

max_tokens

integer

(minimum: 1, maximum: 8192)

Max new tokens to generate

Default: 2048

temperature

number

(minimum: 0, maximum: 5)

Temperature

Default: 0.75

top_p

number

(minimum: 0, maximum: 1)

Top_p

Default: 0.8

image2

file

Optional image you may use in your prompt known as image2

image3

file

Optional image you may use in your prompt known as image3

files_archive

file

An archive of files you mentioned in your prompt if more images are needed

Run this model in Node.js with one line of code:

npx create-replicate --model=nomagick/qwen-vl-chat

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run nomagick/qwen-vl-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nomagick/qwen-vl-chat:e48b42673e1ad0adb765d2a2783338960c0f8a2453ca5aab1445b4afc69749dd",
  {
    input: {
      top_p: 0.8,
      image1: "https://replicate.delivery/pbxt/JfWlCzhD5GBoiDRSmNhMpyYCrmd78lKkLU2JFgr1imbJZIIN/demo.jpeg",
      prompt: "<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nGiven this image: <img>image1</img>, point out where the dog is<|im_end|>\n<|im_start|>assistant\n",
      max_tokens: 2048,
      temperature: 0.75
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run nomagick/qwen-vl-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nomagick/qwen-vl-chat:e48b42673e1ad0adb765d2a2783338960c0f8a2453ca5aab1445b4afc69749dd",
    input={
        "top_p": 0.8,
        "image1": "https://replicate.delivery/pbxt/JfWlCzhD5GBoiDRSmNhMpyYCrmd78lKkLU2JFgr1imbJZIIN/demo.jpeg",
        "prompt": "<|im_start|>system\nYou are a helpful assistant<|im_end|>\n<|im_start|>user\nGiven this image: <img>image1</img>, point out where the dog is<|im_end|>\n<|im_start|>assistant\n",
        "max_tokens": 2048,
        "temperature": 0.75
    }
)

# The nomagick/qwen-vl-chat model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/nomagick/qwen-vl-chat/api#output-schema
    print(item, end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run nomagick/qwen-vl-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "e48b42673e1ad0adb765d2a2783338960c0f8a2453ca5aab1445b4afc69749dd",
    "input": {
      "top_p": 0.8,
      "image1": "https://replicate.delivery/pbxt/JfWlCzhD5GBoiDRSmNhMpyYCrmd78lKkLU2JFgr1imbJZIIN/demo.jpeg",
      "prompt": "<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n<|im_start|>user\\nGiven this image: <img>image1</img>, point out where the dog is<|im_end|>\\n<|im_start|>assistant\\n",
      "max_tokens": 2048,
      "temperature": 0.75
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/nomagick/qwen-vl-chat@sha256:e48b42673e1ad0adb765d2a2783338960c0f8a2453ca5aab1445b4afc69749dd \
  -i 'top_p=0.8' \
  -i 'image1="https://replicate.delivery/pbxt/JfWlCzhD5GBoiDRSmNhMpyYCrmd78lKkLU2JFgr1imbJZIIN/demo.jpeg"' \
  -i $'prompt="<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n<|im_start|>user\\nGiven this image: <img>image1</img>, point out where the dog is<|im_end|>\\n<|im_start|>assistant\\n"' \
  -i 'max_tokens=2048' \
  -i 'temperature=0.75'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/nomagick/qwen-vl-chat@sha256:e48b42673e1ad0adb765d2a2783338960c0f8a2453ca5aab1445b4afc69749dd
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "top_p": 0.8,
      "image1": "https://replicate.delivery/pbxt/JfWlCzhD5GBoiDRSmNhMpyYCrmd78lKkLU2JFgr1imbJZIIN/demo.jpeg",
      "prompt": "<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n<|im_start|>user\\nGiven this image: <img>image1</img>, point out where the dog is<|im_end|>\\n<|im_start|>assistant\\n",
      "max_tokens": 2048,
      "temperature": 0.75
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

Generated in

3.2 seconds

Tweak it Report