dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix "piano" typo (#31027)

This commit is contained in:
Clint Adams 2024-05-28 05:48:23 -04:00 committed by GitHub
parent 8e3b1fef97
commit e18da4e3f2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/models/pop2piano/modeling_pop2piano.py
View File

@ -71,7 +71,7 @@ POP2PIANO_INPUTS_DOCSTRING = r"""
so you should be able to pad the inputs on both the right and the left. Indices can be obtained using so you should be able to pad the inputs on both the right and the left. Indices can be obtained using
[`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for detail. [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for detail.
[What are input IDs?](../glossary#input-ids) To know more on how to prepare `input_ids` for pretraining [What are input IDs?](../glossary#input-ids) To know more on how to prepare `input_ids` for pretraining
take a look a [Pop2Pianp Training](./Pop2Piano#training). take a look a [Pop2Piano Training](./Pop2Piano#training).
attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*): attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**, - 1 for tokens that are **not masked**,