Skip to content

update d_kv'annotation in mt5'configuration #27585

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

Merged
merged 4 commits into from
Nov 23, 2023
Merged

update d_kv'annotation in mt5'configuration #27585

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d398b46
update d_kv'annotation in mt5'configuration
callanwu Nov 19, 2023
43432ab
update d_kv'annotation in mt5'configuration
callanwu Nov 19, 2023
0abaeb1
update d_kv'annotation in mt5'configuration
callanwu Nov 20, 2023
38b9b99
Merge branch 'huggingface:main' into main
callanwu Nov 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/transformers/models/mt5/configuration_mt5.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,8 +40,8 @@ class MT5Config(PretrainedConfig):
d_model (`int`, *optional*, defaults to 512):
Size of the encoder layers and the pooler layer.
d_kv (`int`, *optional*, defaults to 64):
Size of the key, query, value projections per attention head. `d_kv` has to be equal to `d_model //
num_heads`.
Size of the key, query, value projections per attention head. In the conventional context, it is typically expected that `d_kv` has to be equal to `d_model // num_heads`.
But in the architecture of mt5-small, `d_kv` is not equal to `d_model //num_heads`. The `inner_dim` of the projection layer will be defined as `num_heads * d_kv`.
d_ff (`int`, *optional*, defaults to 1024):
Size of the intermediate feed forward layer in each `T5Block`.
num_layers (`int`, *optional*, defaults to 8):
Expand Down