---
license: mit
---

## Quick Start

```python
from vllm import LLM, SamplingParams
from PIL import Image

model_name = "RUC-AIBOX/Virgo-72B"
placeholder = "<|image_pad|>"
llm = LLM(
        model=model_name,
        trust_remote_code=True,
        tensor_parallel_size=8,
    )
question = "Please first think deeply about the question, and then put the final answer in \\boxed{}.\nIn the diagram, $\\angle E A D=90^{\\circ}, \\angle A C D=90^{\\circ}$, and $\\angle A B C=90^{\\circ}$. Also, $E D=13, E A=12$, $D C=4$, and $C B=2$. Determine the length of $A B$."
prompt = ("<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"
              f"<|im_start|>user\n<|vision_start|>{placeholder}<|vision_end|>"
              f"{question}<|im_end|>\n"
              "<|im_start|>assistant\n")
stop_token_ids = None
sampling_params = SamplingParams(
    temperature=0.0,
    top_k=1,
    top_p=1.0,
    stop_token_ids=stop_token_ids,
    repetition_penalty=1.05,
    max_tokens=8192
)
image = Image.open("case/2246_image_1.jpg")
inputs = {
            "prompt": prompt,
            "multi_modal_data": {
                "image": image
            },
        }
outputs = llm.generate(inputs, sampling_params)
print(outputs[0].outputs[0].text)