Upload BertForSequenceClassification

config.json

@@ -1,8 +1,12 @@
 {
   "affine": true,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
   "attention_probs_dropout_prob": 0.1,
   "auto_map": {
-    "AutoConfig": "configuration_bert.BertConfig"
+    "AutoConfig": "configuration_bert.BertConfig",
+    "AutoModelForSequenceClassification": "modeling_bert.BertForSequenceClassification"
   },
   "classifier_dropout": null,
   "hidden_act": "gelu",
@@ -17,6 +21,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
   "transformers_version": "4.33.3",
   "type_vocab_size": 2,
   "use_cache": true,

modeling_bert.py

@@ -16,7 +16,8 @@ from transformers.models.bert.modeling_bert import (
 )
 from transformers.modeling_outputs import (
     BaseModelOutputWithPoolingAndCrossAttentions, 
-    SequenceClassifierOutput
+    SequenceClassifierOutput, 
+    MultipleChoiceModelOutput
 )
 
 from .configuration_bert import BertConfig
@@ -293,3 +294,80 @@ class BertForSequenceClassification(BertPreTrainedModel):
             hidden_states=outputs.hidden_states,
             attentions=outputs.attentions,
         )
+
+
+class BertForMultipleChoice(BertPreTrainedModel):
+
+    def __init__(self, config):
+        super().__init__(config)
+
+        self.bert = BertModel(config)
+        classifier_dropout = (
+            config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
+        )
+        self.dropout = nn.Dropout(classifier_dropout)
+        self.classifier = nn.Linear(config.hidden_size, 1)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def forward(
+        self,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple[torch.Tensor], MultipleChoiceModelOutput]:
+    
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        num_choices = input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1]
+
+        input_ids = input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None
+        attention_mask = attention_mask.view(-1, attention_mask.size(-1)) if attention_mask is not None else None
+        token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1)) if token_type_ids is not None else None
+        position_ids = position_ids.view(-1, position_ids.size(-1)) if position_ids is not None else None
+        inputs_embeds = (
+            inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1))
+            if inputs_embeds is not None
+            else None
+        )
+
+        outputs = self.bert(
+            input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            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,
+        )
+
+        pooled_output = outputs[1]
+
+        pooled_output = self.dropout(pooled_output)
+        logits = self.classifier(pooled_output)
+        reshaped_logits = logits.view(-1, num_choices)
+
+        loss = None
+        if labels is not None:
+            loss_fct = nn.CrossEntropyLoss()
+            loss = loss_fct(reshaped_logits, labels)
+
+        if not return_dict:
+            output = (reshaped_logits,) + outputs[2:]
+            return ((loss,) + output) if loss is not None else output
+
+        return MultipleChoiceModelOutput(
+            loss=loss,
+            logits=reshaped_logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994c6ca6ce911a444ebac151fbe611c63ba1d26c14438d690b2ea071958f419a
+oid sha256:b0e4d45385d6072711fe037338b7d41b4c82e7310bfec45c493ee84f649432b7
 size 438000689