'VisionAttention' object has no attribute 'head_dim'
#7
by
Zophe
- opened
I used the following command to install the transformers library: 'pip install -U git+https://github.com/huggingface/transformers' to install transformers.
transformers.version = 4.45.0.dev0
I encountered this error while running the official demo without qwen_vl_utils: 'AttributeError: 'VisionAttention' object has no attribute 'head_dim''.
Can anyone help me resolve this issue?
Has this issue been fixed or not, meet the same error.
please refer to this post https://juejin.cn/post/7410728156854239284
chenkq
changed discussion status to
closed