add model

rita_modeling.py

@@ -226,19 +226,20 @@ class RITAModel(PreTrainedModel):
     def forward(
         self,
         input_ids=None,
-        past_key_values=None,
+        past_key_values=None,  # NOT USED
         attention_mask=None,
-        token_type_ids=None,
-        position_ids=None,
-        head_mask=None,
+        token_type_ids=None, # NOT USED
+        position_ids=None, # NOT USED
+        head_mask=None, # NOT USED
         inputs_embeds=None,
-        encoder_hidden_states=None,
-        encoder_attention_mask=None,
+        encoder_hidden_states=None,  # NOT USED
+        encoder_attention_mask=None, # NOT USED
         labels=None,
-        use_cache=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None) -> torch.FloatTensor:
+        use_cache=None, # NOT USED
+        output_attentions=None, # NOT USED
+        output_hidden_states=None, # NOT USED
+        return_dict=None # NOT USED
+        ) -> torch.FloatTensor:
         
         if inputs_embeds == None:
             x = self.embedding(input_ids)  # N x L x D