ValueError: Unrecognized configuration class ＜class ‘transformers.models.qwen2_vl.....完美解决方案

最近在复现Qwen2-VL-7B-Instruct这个大模型，链接：https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct

问题与解决方案

我先把我遇到的问题和解决方案写在前方：

报错信息：ValueError: Unrecognized configuration class <class ‘transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLConfig’> for this kind of AutoModel: AutoModelForCausalLM.

原因：Qwen2VLForConditionalGeneration在Qwen2-VL-7B-Instruct中不能加载
官方解决方案：https://github.com/QwenLM/Qwen2-VL/issues/43

简单总结：将

from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig；model_name_or_path = "Qwen/Qwen2-VL-7B-Instruct"

修改为：

from transformers import Qwen2VLForConditionalGeneration
model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")

即可

Qwen2-VL-7B-Instruct 模型功能

Qwen2-VL-7B-Instruct 是一个多模态大模型，功能主要包括：读取本地或者链接图片，输出图片内容；对比两幅图像（本地或者在线连接）的内容；读取本地视频（mp4格式）内容等，也比较好玩。先给大家看hugging face中的模型model card中的快速复现代码：

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# default: Load the model on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen2-VL-7B-Instruct",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# default processer
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")

# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

扩展功能：

# You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
## Local file path
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/your/image.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
## Image URL
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "http://path/to/your/image.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
## Base64 encoded image
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "data:image;base64,/9j/..."},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

这个模型还是很好玩的，感兴趣的小伙伴可以试试！