llama4

from mistralrs 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="Q4K",
)

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,
        presence_penalty=1.0,
        top_p=0.1,
        temperature=0.1,
    )
)
print(res.choices[0].message.content)
print(res.usage)