llava_next

Runnable Python SDK example llava_next.

from mistralrs import Runner, Which, ChatCompletionRequest, MultimodalArchitecture

runner = Runner(
    which=Which.MultimodalPlain(
        model_id="llava-hf/llava-v1.6-mistral-7b-hf",
        arch=MultimodalArchitecture.LLaVANext,
    ),
)

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 shown in this image? Write a detailed response analyzing the scene.",
                    },
                ],
            }
        ],
        max_tokens=256,
        presence_penalty=1.0,
        top_p=0.1,
        temperature=0.1,
    )
)
print(res.choices[0].message.content)
print(res.usage)

Source: examples/python/llava_next.py