Fix Typo (#24530)

* Fix Typo

* Fix all copies

src/transformers/models/bart/modeling_bart.py

@@ -319,7 +319,7 @@ class BartEncoderLayer(nn.Module):
     ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]:
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
+            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
             attention_mask (`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (`torch.FloatTensor`): mask for attention heads in a given layer of size

src/transformers/models/blenderbot_small/modeling_blenderbot_small.py

@@ -304,7 +304,7 @@ class BlenderbotSmallEncoderLayer(nn.Module):
     ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]:
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
+            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
             attention_mask (`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (`torch.FloatTensor`): mask for attention heads in a given layer of size

src/transformers/models/marian/modeling_marian.py

@@ -322,7 +322,7 @@ class MarianEncoderLayer(nn.Module):
     ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]:
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
+            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
             attention_mask (`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (`torch.FloatTensor`): mask for attention heads in a given layer of size

src/transformers/models/plbart/modeling_plbart.py

@@ -315,7 +315,7 @@ class PLBartEncoderLayer(nn.Module):
     ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]:
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
+            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
             attention_mask (`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (`torch.FloatTensor`): mask for attention heads in a given layer of size

src/transformers/models/time_series_transformer/modeling_time_series_transformer.py

@@ -484,7 +484,7 @@ class TimeSeriesTransformerEncoderLayer(nn.Module):
     ) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]:
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
+            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
             attention_mask (`torch.FloatTensor`): attention mask of size
                 `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             layer_head_mask (`torch.FloatTensor`): mask for attention heads in a given layer of size