File tree Expand file tree Collapse file tree 1 file changed +4
-0
lines changed
src/diffusers/pipelines/kolors Expand file tree Collapse file tree 1 file changed +4
-0
lines changed Original file line number Diff line number Diff line change @@ -277,6 +277,7 @@ def _pad(
277
277
padding_strategy : PaddingStrategy = PaddingStrategy .DO_NOT_PAD ,
278
278
pad_to_multiple_of : Optional [int ] = None ,
279
279
return_attention_mask : Optional [bool ] = None ,
280
+ padding_side : Optional [bool ] = None ,
280
281
) -> dict :
281
282
"""
282
283
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
@@ -298,6 +299,9 @@ def _pad(
298
299
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
299
300
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
300
301
`>= 7.5` (Volta).
302
+ padding_side (`str`, *optional*):
303
+ The side on which the model should have padding applied. Should be selected between ['right', 'left'].
304
+ Default value is picked from the class attribute of the same name.
301
305
return_attention_mask:
302
306
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
303
307
"""
You can’t perform that action at this time.
0 commit comments