qwen2.5-vl-7b-instruct

# Enable memory-efficient attention
model = Qwen2VLForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    use_flash_attention_2=True,  # Requires flash-attn installed
    low_cpu_mem_usage=True
)

from PIL import Image

# Resize large images to reduce memory usage
def preprocess_image(image_path, max_size=1024):
    image = Image.open(image_path)
    image.thumbnail((max_size, max_size), Image.LANCZOS)
    return image