Files
engine/docs/QWEN2VL.md

4.6 KiB

Qwen 2 Vision Model: Qwen2-VL Collection

Hanzo Engine supports the Qwen2-VL multimodal model family. ISQ quantization is supported to allow running the model with less memory requirements.

UQFF quantizations are also available.

Note: When using device mapping or model topology, only the text model and its layers will be managed. This is because it contains most of the model parameters. The text model has 28 layers.

Quick Start

hanzo run -m Qwen/Qwen2-VL-2B-Instruct --isq 4 --image photo.jpg -i "Describe this image"

Input Formats

The Python and HTTP APIs support sending inputs as:

  • Images: URL, path to a local file, or base64 encoded string (via image_url)

The Rust SDK takes images from the image crate.

HTTP API

  1. Start the server
hanzo serve -m Qwen/Qwen2-VL-2B-Instruct --isq 4 -p 1234
  1. Send a request
from openai import OpenAI

client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")

completion = client.chat.completions.create(
    model="default",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg"
                    },
                },
                {
                    "type": "text",
                    "text": "What is this?",
                },
            ],
        },
    ],
    max_tokens=256,
)
print(completion.choices[0].message.content)

Python SDK

You can find this example here.

from hanzo import Runner, Which, ChatCompletionRequest, MultimodalArchitecture

MODEL_ID = "Qwen/Qwen2-VL-2B-Instruct"

runner = Runner(
    which=Which.MultimodalPlain(
        model_id=MODEL_ID,
        arch=MultimodalArchitecture.Qwen2VL,
    ),
)

res = runner.send_chat_completion_request(
    ChatCompletionRequest(
        model="default",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg"
                        },
                    },
                    {
                        "type": "text",
                        "text": "What is this?",
                    },
                ],
            }
        ],
        max_tokens=256,
    )
)
print(res.choices[0].message.content)
print(res.usage)

Rust SDK

You can find this example here.

use anyhow::Result;
use hanzo::{IsqType, TextMessageRole, MultimodalMessages, MultimodalModelBuilder};

const MODEL_ID: &str = "Qwen/Qwen2-VL-2B-Instruct";

#[tokio::main]
async fn main() -> Result<()> {
    let model =
        MultimodalModelBuilder::new(MODEL_ID)
            .with_isq(IsqType::Q4K)
            .with_logging()
            .build()
            .await?;

    let bytes = match reqwest::blocking::get(
        "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg",
    ) {
        Ok(http_resp) => http_resp.bytes()?.to_vec(),
        Err(e) => anyhow::bail!(e),
    };
    let image = image::load_from_memory(&bytes)?;

    let messages = MultimodalMessages::new().add_image_message(
        TextMessageRole::User,
        "What is this?",
        vec![image],
    );

    let response = model.send_chat_request(messages).await?;

    println!("{}", response.choices[0].message.content.as_ref().unwrap());
    dbg!(
        response.usage.avg_prompt_tok_per_sec,
        response.usage.avg_compl_tok_per_sec
    );

    Ok(())
}