Qwen2.5-VL *B模型 SFT训练&使用vllm推理报错：AttributeError: 'NoneType' object has no attribute 'image_processor'

[BD-MF]

Reminder

• I have read the above rules and searched the existing issues.

System Info

使用LLaMA-Factory仓库最新版代码，和tranformers最新版4.49.0.dev0 进行Qwen2.5-VL-3B和7B模型的SFT和基于VLLM进行推理均报错：

Reproduction

Put your message here.

Others

No response

[BD-MF]

Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/multiprocess/pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py", line 678, in _write_generator_to_queue
for i, result in enumerate(func(**kwargs)):
File "/usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py", line 3458, in _map_single
batch = apply_function_on_filtered_inputs(
File "/usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py", line 3320, in apply_function_on_filtered_inputs
processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
File "/mnt/public02/usr/yinzheng/LLaMA-Factory/src/llamafactory/data/processor/unsupervised.py", line 69, in preprocess_dataset
input_ids, labels = self._encode_data_example(
File "/mnt/public02/usr/yinzheng/LLaMA-Factory/src/llamafactory/data/processor/unsupervised.py", line 46, in _encode_data_example
messages = self.template.mm_plugin.process_messages(messages, images, videos, audios, self.processor)
File "/mnt/public02/usr/yinzheng/LLaMA-Factory/src/llamafactory/data/mm_plugin.py", line 1094, in process_messages
image_processor: "BaseImageProcessor" = getattr(processor, "image_processor")
AttributeError: 'NoneType' object has no attribute 'image_processor'

[hiyouga]

see huggingface/transformers#36164 (comment)

[BD-MF]

意思是：修改模型的preprocessor_config.json中的image_processor_type为‘Qwen2VLImageProcessor’就可以了么

[MengHao666]

意思是：修改模型的preprocessor_config.json中的image_processor_type为‘Qwen2VLImageProcessor’就可以了么

Have you solved this problem?

[YuanDaoze]

意思是：修改模型的preprocessor_config.json中的image_processor_type为‘Qwen2VLImageProcessor’就可以了么
您好！我也想用llama factory训练Qwen2.5-VL ，但是我安装vllm的时候会报错，方便知道你的环境版本吗？比如torch用的是什么版本呀？