We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
看了代码后,对vision-rope和m-rope的理解如下:
1、图片内部的vision-rope:head_dim=80, freq =(0,40,2)# last_dim=20, cat(hw)=40 此时h和w的freq都是独立的从0-40 2、多模态m-rope:head_dim=128,inv_freq =(0,128, 2)# last_dim=64,mrope-section=[16,24,24], 则h的freq是从16 * 2 - 40 * 2,而w的freq是从41 * 2 - 64 * 2
1、请教下上述理解有问题吗? 2、如果上述理解问题不大的话,想问下对于视觉内部hw是独立编码freq容易理解,但对于多模态让hw维度的freq不一致是有什么考虑吗
The text was updated successfully, but these errors were encountered:
No branches or pull requests
看了代码后,对vision-rope和m-rope的理解如下:
1、图片内部的vision-rope:head_dim=80, freq =(0,40,2)# last_dim=20, cat(hw)=40 此时h和w的freq都是独立的从0-40
2、多模态m-rope:head_dim=128,inv_freq =(0,128, 2)# last_dim=64,mrope-section=[16,24,24], 则h的freq是从16 * 2 - 40 * 2,而w的freq是从41 * 2 - 64 * 2
1、请教下上述理解有问题吗?
2、如果上述理解问题不大的话,想问下对于视觉内部hw是独立编码freq容易理解,但对于多模态让hw维度的freq不一致是有什么考虑吗
The text was updated successfully, but these errors were encountered: