Qianfan-VL：领域增强型通用视觉语言模型

pip install transformers accelerate torch torchvision pillow einops 

import torch
import torchvision.transforms as T
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer
from PIL import Image

IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform

def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio

def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # calculate the existing image aspect ratio
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # find the closest aspect ratio to the target
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # calculate the target width and height
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # resize the image
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        # split the image
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images

def load_image(image_file, input_size=448, max_num=12):
    image = Image.open(image_file).convert('RGB')
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values

# Load model
MODEL_PATH = "baidu/Qianfan-VL-8B"  # or Qianfan-VL-3B, Qianfan-VL-70B
model = AutoModel.from_pretrained(
    MODEL_PATH,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto"
).eval()
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)

# Load and process image
pixel_values = load_image("./example/scene_ocr.png").to(torch.bfloat16)

# Inference
prompt = "<image>请识别图中所有文字"
with torch.no_grad():
    response = model.chat(
        tokenizer,
        pixel_values=pixel_values,
        question=prompt,
        generation_config={"max_new_tokens": 512},
        verbose=False
    )
print(response)

docker run -d --name qianfan-vl \
  --gpus all \
  -v /path/to/Qianfan-VL-8B:/model \
  -p 8000:8000 \
  --ipc=host \
  vllm/vllm-openai:latest \
  --model /model \
  --served-model-name qianfan-vl \
  --trust-remote-code \
  --hf-overrides '{"architectures":["InternVLChatModel"],"model_type":"internvl_chat"}'

curl 'http://127.0.0.1:8000/v1/chat/completions' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qianfan-vl",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": {
              "url": "https://qianfan-public-demo.bj.bcebos.com/qianfan-vl/2509/images/scene_ocr.png"
            }
          },
          {
            "type": "text",
            "text": "<image>请识别图中所有文字"
          }
        ]
      }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="EMPTY",
    base_url="http://127.0.0.1:8000/v1"
)

response = client.chat.completions.create(
    model="qianfan-vl",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url": "https://qianfan-public-demo.bj.bcebos.com/qianfan-vl/2509/images/scene_ocr.png"}
                },
                {
                    "type": "text",
                    "text": "<image>请描述这张图片"
                }
            ]
        }
    ],
    max_tokens=512
)
print(response.choices[0].message.content)

@misc{qianfan-vl-2025,
  title={Qianfan-VL: Domain-Enhanced Universal Vision-Language Models},
  author={Qianfan Team},
  year={2025},
  publisher={Baidu}
}