transformers
Add a use_parallel_residual argument to control the residual computing way
#18695

Merged

Add a use_parallel_residual argument to control the residual computing way #18695

sgugger merged 3 commits into huggingface:main from main

NinedayWang marked this pull request as draft 3 years ago

NinedayWang marked this pull request as ready for review 3 years ago

sgugger commented on 2022-09-14

Add a gpt_j_residual argument to control the residual computing way

328e0643

Put duplicate code outside of the if block

70aaec5c

Rename parameter "gpt_j_residual" to "use_parallel_residual" and set …

4c12b692

patrickvonplaten commented on 2022-09-27

patrickvonplaten changed the title ~~Add a gpt_j_residual argument to control the residual computing way~~ Add a use_parallel_residual argument to control the residual computing way 3 years ago

patrickvonplaten approved these changes on 2022-09-27

sgugger approved these changes on 2022-09-27

sgugger merged 226b0e46 into main 3 years ago

Reviewers

sgugger

patrickvonplaten

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

transformers Add a use_parallel_residual argument to control the residual computing way #18695 Merged

Add a use_parallel_residual argument to control the residual computing way #18695

transformers
Add a use_parallel_residual argument to control the residual computing way
#18695

Merged