Actions: keras-team/keras
Actions
2,106 workflow runs
2,106 workflow runs
attention_mask
computation in MultiHeadAttention
Labeler
#2087:
Pull request #20488
opened
by
james77777778
return_attention_scores
from _compute_attention
Labeler
#2081:
Pull request #20482
edited
by
divyashreepathihalli
return_attention_scores
from _compute_attention
Labeler
#2080:
Pull request #20482
edited
by
divyashreepathihalli
return_attention_scores
from _compute_attention
Labeler
#2079:
Pull request #20482
edited
by
divyashreepathihalli
return_attention_scores
from _compute_attention
Labeler
#2078:
Pull request #20482
opened
by
divyashreepathihalli
OrderedDict
with optree and related documentation.
Labeler
#2077:
Pull request #20481
opened
by
hertschuh
CompileLoss
: Better handling of partial loss configs
Labeler
#2074:
Pull request #20478
opened
by
nicolaspi
CompileLoss
: fix for partially defined loss with different y_pred
and y_true
structures
Labeler
#2071:
Pull request #20477
opened
by
nicolaspi