Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
2.33k
stars
130
forks
source link
use Qwen2VLModel in huggingface got an unexpected keyword argument 'pixel_values' #266
Open
mearcstapa-gqz opened 2 days ago
TypeError: Qwen2VLModel.forward() got an unexpected keyword argument 'pixel_values'
I assume Qwen2VLModel should be used to get hidden states from text and image input, but looks like the normal pipeline fails