Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[Feed Forward Network] Commons #13

Open
jinmang2 opened this issue Jun 20, 2022 · 1 comment
Open

[Feed Forward Network] Commons #13

jinmang2 opened this issue Jun 20, 2022 · 1 comment
Assignees
@jinmang2
Labels
features feed forward network

Comments

@jinmang2
Copy link
Owner

jinmang2 commented Jun 20, 2022 •
edited
Loading

목적: 다양한 형태의 Fully Connected Layer 구현
@jinmang2 jinmang2 self-assigned this Jun 20, 2022
@jinmang2
Copy link
Owner Author

jinmang2 commented Jun 21, 2022 •
edited
Loading

모델별 체크리스트

  • pre vs post layernorm
  • residual connection
  • grouped linear
  • deberta style
  • intermediate-output class vs functional
  • class 하나로 처리 vs code context를 봐야 하는지
  • nn.Linear vs nn.Conv1D
  • intermediate size가 fixed인지 various한지
  • activation function
  • apply_chunking_to_forward 유/무

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@jinmang2 jinmang2

Labels
features feed forward network
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jinmang2