import torch
from transformers import AutoProcessor, AutoModelForCausalLM
model_name = "Hon-Wong/VoRA-7B-Instruct"
processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
conversation = [
    {
        "role":"user",
        "content":[
            {
                "type":"image",
                "url": "{image path or url}"
            },
            {
                "type":"text",
                "text":"<image> Describe this image."
            }
        ]
    }
]
model_inputs = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=True, return_tensors='pt', return_dict=True).to(model.device)
gen_kwargs = {"max_new_tokens": 1024, "eos_token_id": processor.tokenizer.eos_token_id}

with torch.inference_mode():
    outputs = model.generate(model_inputs, **gen_kwargs)
    output_text = processor.tokenizer.batch_decode(
        outputs, skip_special_tokens=True
    )
    print(output_text)