Fix shapes in model docstrings (#15696)

src/transformers/models/bart/modeling_bart.py

@@ -294,11 +294,11 @@ class BartEncoderLayer(nn.Module):
     ):
         """
         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 `(seq_len, batch, 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.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                 returned tensors for more detail.
@@ -377,17 +377,17 @@ class BartDecoderLayer(nn.Module):
     ):
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape *(batch, seq_len, 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.
+                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             encoder_hidden_states (`torch.FloatTensor`):
-                cross attention input to the layer of shape *(batch, seq_len, embed_dim)*
+                cross attention input to the layer of shape `(batch, seq_len, embed_dim)`
             encoder_attention_mask (`torch.FloatTensor`): encoder attention mask of size
-                *(batch, 1, tgt_len, src_len)* where padding elements are indicated by very large negative values.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             cross_attn_layer_head_mask (`torch.FloatTensor`): mask for cross-attention heads in a given layer of
-                size *(decoder_attention_heads,)*.
+                size `(decoder_attention_heads,)`.
             past_key_value (`Tuple(torch.FloatTensor)`): cached past key and value projection states
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under

src/transformers/models/blenderbot_small/modeling_blenderbot_small.py

@@ -295,11 +295,11 @@ class BlenderbotSmallEncoderLayer(nn.Module):
     ):
         """
         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 `(seq_len, batch, 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.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                 returned tensors for more detail.
@@ -379,17 +379,17 @@ class BlenderbotSmallDecoderLayer(nn.Module):
     ):
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape *(batch, seq_len, 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.
+                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             encoder_hidden_states (`torch.FloatTensor`):
-                cross attention input to the layer of shape *(batch, seq_len, embed_dim)*
+                cross attention input to the layer of shape `(batch, seq_len, embed_dim)`
             encoder_attention_mask (`torch.FloatTensor`): encoder attention mask of size
-                *(batch, 1, tgt_len, src_len)* where padding elements are indicated by very large negative values.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             cross_attn_layer_head_mask (`torch.FloatTensor`): mask for cross-attention heads in a given layer of
-                size *(decoder_attention_heads,)*.
+                size `(decoder_attention_heads,)`.
             past_key_value (`Tuple(torch.FloatTensor)`): cached past key and value projection states
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under

src/transformers/models/marian/modeling_marian.py

@@ -312,11 +312,11 @@ class MarianEncoderLayer(nn.Module):
     ):
         """
         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 `(seq_len, batch, 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.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                 returned tensors for more detail.
@@ -396,17 +396,17 @@ class MarianDecoderLayer(nn.Module):
     ):
         """
         Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape *(batch, seq_len, 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.
+                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
             encoder_hidden_states (`torch.FloatTensor`):
-                cross attention input to the layer of shape *(batch, seq_len, embed_dim)*
+                cross attention input to the layer of shape `(batch, seq_len, embed_dim)`
             encoder_attention_mask (`torch.FloatTensor`): encoder attention mask of size
-                *(batch, 1, tgt_len, src_len)* where padding elements are indicated by very large negative values.
+                `(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
-                *(encoder_attention_heads,)*.
+                `(encoder_attention_heads,)`.
             cross_attn_layer_head_mask (`torch.FloatTensor`): mask for cross-attention heads in a given layer of
-                size *(decoder_attention_heads,)*.
+                size `(decoder_attention_heads,)`.
             past_key_value (`Tuple(torch.FloatTensor)`): cached past key and value projection states
             output_attentions (`bool`, *optional*):
                 Whether or not to return the attentions tensors of all attention layers. See `attentions` under