在按步骤配置完环境后，MiniCPM-2-6_v的生成出现了如下问题

[eternal-god3]

VisRAG-Ret load success!
VisRAG-Gen (MiniCPM-V-2_6) load begin...
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████| 4/4 [00:01<00:00, 2.79it/s]
VisRAG-Gen (MiniCPM-V-2_6) load success!
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
File "/home/lzr24/VisRAG/scripts/demo/visrag_pipeline/answer.py", line 152, in
answer = answer_question(images_topk, query)
File "/home/lzr24/VisRAG/scripts/demo/visrag_pipeline/answer.py", line 88, in answer_question
answer = gen_model.chat(
File "/home/lzr24/.cache/huggingface/modules/transformers_modules/openbmb/MiniCPM-V-2_6/c63b9ff4b3c84b23ff6685eb3764c6a76a38432a/modeling_minicpmv.py", line 309, in chat
assert self.config.query_num == processor.image_processor.image_feature_size, "These two values should be the same. Check config.json and preprocessor_config.json."
AttributeError: 'MiniCPMVTokenizerFast' object has no attribute 'image_processor'

请问可以帮忙解答我的疑惑吗？感谢！