Add type hints for M2M (#18998)

* added type hints

* fixed typo

src/transformers/models/m2m_100/modeling_m2m_100.py

@@ -17,7 +17,7 @@
 
 import math
 import random
-from typing import Optional, Tuple, Union
+from typing import List, Optional, Tuple, Union
 
 import torch
 from torch import nn
@@ -712,13 +712,13 @@ class M2M100Encoder(M2M100PreTrainedModel):
 
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        head_mask=None,
-        inputs_embeds=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
     ):
         r"""
         Args:
@@ -887,18 +887,18 @@ class M2M100Decoder(M2M100PreTrainedModel):
 
     def forward(
         self,
-        input_ids=None,
-        attention_mask=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
-        head_mask=None,
-        cross_attn_head_mask=None,
-        past_key_values=None,
-        inputs_embeds=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        cross_attn_head_mask: Optional[torch.Tensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
     ):
         r"""
         Args: