mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
4.6 KiB
4.6 KiB
Llama 4 Series: meta-llama/Llama-4-Scout-17B-16E-Instruct
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences.
Architecture:
- Efficient inference: 17B activated parameters
- Very sparse: 1 activated expert for both Scout (of 16), and Maverick (of 128)
- RoPE enhancement: iRoPE enables high context-length functionality
Integration in Hanzo Engine:
- Tool calling + Automatic web search
- ISQ
Quick Start
hanzo run -m meta-llama/Llama-4-Scout-17B-16E-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
- Start the server
hanzo serve -m meta-llama/Llama-4-Scout-17B-16E-Instruct --isq 4 -p 1234
- 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)
- You can find an example of encoding the image via base64 here.
- You can find an example of loading an image locally here.
Python SDK
You can find this example here.
from hanzo import Runner, Which, ChatCompletionRequest, MultimodalArchitecture
runner = Runner(
which=Which.MultimodalPlain(
model_id="meta-llama/Llama-4-Scout-17B-16E-Instruct",
arch=MultimodalArchitecture.Llama4,
),
in_situ_quant="4",
)
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)
- You can find an example of encoding the image via base64 here.
- You can find an example of loading an image locally here.
Rust SDK
You can find this example here.
use anyhow::Result;
use hanzo::{IsqType, TextMessageRole, MultimodalMessages, MultimodalModelBuilder};
#[tokio::main]
async fn main() -> Result<()> {
let model = MultimodalModelBuilder::new(
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
)
.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(())
}