-
Notifications
You must be signed in to change notification settings - Fork 72
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TinyChart-visual encoder位置编码长度不匹配的错误 #86
Comments
你好,
|
您好,我也遇到了同样的问题, 请问解决方案是什么? |
首先感谢您的精彩工作。
目前我正在基于tinyllava模型利用tinychart数据复现训练流程,但是我发现bczhou/TinyLLaVA-3.1B-SigLIP中的visual encoder的image_size是384,vit_add_tome.py会将config中的image_size改成768。
因此在模型初始化时会基于image_size=768初始化sigLIP的position embedding的长度,但是bczhou/TinyLLaVA-3.1B-SigLIP checkpoint中的position embedding长度是基于image_size = 384的。将这个checkpoint中的参数load进来时导致了我在运行时产生了参数形状不匹配的错误。
能否请问下如何解决这个错误呢?非常感谢!
The text was updated successfully, but these errors were encountered: