Update modeling_hf_nomic_bert.py

modeling_hf_nomic_bert.py

@@ -1694,7 +1694,6 @@ class NomicBertModel(NomicBertPreTrainedModel):
         return_dict=None,
         matryoshka_dim=None,
         inputs_embeds=None,
-        head_mask=None,
     ):
         if input_ids is not None and inputs_embeds is not None:
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
@@ -1918,10 +1917,6 @@ class NomicBertForMultipleChoice(NomicBertPreTrainedModel):
             position_ids=position_ids,
             head_mask=head_mask,
             inputs_embeds=inputs_embeds,
-            output_attentions=output_attentions,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-            unpad_inputs=unpad_inputs,
         )
 
         pooled_output = outputs[1]
@@ -1987,9 +1982,6 @@ class NomicBertForTokenClassification(NomicBertPreTrainedModel):
             position_ids=position_ids,
             head_mask=head_mask,
             inputs_embeds=inputs_embeds,
-            output_attentions=output_attentions,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
         )
 
         sequence_output = outputs[0]
@@ -1999,7 +1991,7 @@ class NomicBertForTokenClassification(NomicBertPreTrainedModel):
 
         loss = None
         if labels is not None:
-            loss_fct = CrossEntropyLoss()
+            loss_fct = nn.CrossEntropyLoss()
             loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
 
         if not return_dict:
@@ -2057,9 +2049,6 @@ class NomicBertForQuestionAnswering(NomicBertPreTrainedModel):
             position_ids=position_ids,
             head_mask=head_mask,
             inputs_embeds=inputs_embeds,
-            output_attentions=output_attentions,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
         )
 
         sequence_output = outputs[0]
@@ -2081,7 +2070,7 @@ class NomicBertForQuestionAnswering(NomicBertPreTrainedModel):
             start_positions = start_positions.clamp(0, ignored_index)
             end_positions = end_positions.clamp(0, ignored_index)
 
-            loss_fct = CrossEntropyLoss(ignore_index=ignored_index)
+            loss_fct = nn.CrossEntropyLoss(ignore_index=ignored_index)
             start_loss = loss_fct(start_logits, start_positions)
             end_loss = loss_fct(end_logits, end_positions)
             total_loss = (start_loss + end_loss) / 2