OpenMed/Ministral-3B-MedVL

from transformers import AutoProcessor, AutoModelForImageTextToText

model_id = "OpenMed/Ministral-3B-MedVL"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://example.com/xray.jpg"},
            {"type": "text", "text": "What are the key findings in this chest X-ray?"},
        ],
    }
]

inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

from vllm import LLM, SamplingParams

llm = LLM(
    model="OpenMed/Ministral-3B-MedVL",
    tokenizer_mode="mistral",
    config_format="mistral",
    load_format="mistral",
    max_model_len=4096,
    limit_mm_per_prompt={"image": 1},
)

messages = [{"role": "user", "content": [
    {"type": "image_url", "image_url": {"url": "https://example.com/xray.jpg"}},
    {"type": "text", "text": "What are the key findings in this chest X-ray?"},
]}]

output = llm.chat(messages, SamplingParams(temperature=0, max_tokens=512))
print(output[0].outputs[0].text)

# Launch server
python -m sglang.launch_server --model-path OpenMed/Ministral-3B-MedVL --port 8000

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="OpenMed/Ministral-3B-MedVL",
    messages=[{"role": "user", "content": [
        {"type": "image_url", "image_url": {"url": "https://example.com/xray.jpg"}},
        {"type": "text", "text": "What are the key findings in this chest X-ray?"},
    ]}],
    max_tokens=512,
)
print(response.choices[0].message.content)