Adding SequenceClassification model/head to impl

README.md

@@ -9044,6 +9044,11 @@ model-index:
     task:
       type: PairClassification
 ---
+
+--- 
+> [!IMPORTANT]
+> This is a fork of the original [snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) model, which was released under the Apache 2.0 license. 
+--- 
 <h1 align="center">Snowflake's Arctic-embed-m-v2.0</h1>
 <h4 align="center">
    <p>
@@ -9213,4 +9218,4 @@ You also can email Daniel Campos([email protected]).
 
 
 ## License
-Arctic is licensed under the [Apache-2](https://www.apache.org/licenses/LICENSE-2.0). The released models can be used for commercial purposes free of charge.
+Arctic is licensed under the [Apache-2](https://www.apache.org/licenses/LICENSE-2.0). The released models can be used for commercial purposes free of charge.

config.json

@@ -6,6 +6,7 @@
   "auto_map": {
     "AutoConfig": "configuration_hf_alibaba_nlp_gte.GteConfig",
     "AutoModel": "modeling_hf_alibaba_nlp_gte.GteModel"
+    "AutoModelForSequenceClassification": "modeling_hf_alibaba_nlp_gte.GteForSequenceClassification"
   },
   "classifier_dropout": 0.1,
   "hidden_act": "gelu",

modeling_hf_alibaba_nlp_gte.py

@@ -26,11 +26,7 @@ from transformers.activations import ACT2FN
 from transformers.modeling_outputs import (
     BaseModelOutput,
     BaseModelOutputWithPooling,
-    MaskedLMOutput,
-    MultipleChoiceModelOutput,
-    QuestionAnsweringModelOutput,
-    SequenceClassifierOutput,
-    ModelOutput,
+    SequenceClassifierOutputWithPast,
 )
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import logging
@@ -965,3 +961,63 @@ class GteModel(GtePreTrainedModel):
             hidden_states=encoder_outputs.hidden_states,
             attentions=encoder_outputs.attentions,
         )
+
+
+class GteForSequenceClassification(GtePreTrainedModel):
+
+    def __init__(self, config: GteConfig):
+
+        self.config = config
+        self.num_labels = 1
+        self.model = GteModel(config, add_pooling_layer=True)
+
+        self.score = nn.Linear(config.hidden_size, self.num_labels, bias=False)
+        self.loss_function = nn.MSELoss()
+
+    def get_input_embeddings(self):
+        return self.model.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.model.embed_tokens = value
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+    ) -> SequenceClassifierOutputWithPast:
+        r"""
+        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
+            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
+            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
+            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
+        """
+
+        transformer_outputs = self.model(
+            input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            inputs_embeds=inputs_embeds,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+        )
+        hidden_states = transformer_outputs.pooler_output
+
+        logits = self.score(hidden_states)
+
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits.squeeze(-1), labels.squeeze(-1))
+
+        return SequenceClassifierOutputWithPast(
+            loss=loss,
+            logits=logits,
+            hidden_states=transformer_outputs.hidden_states,
+            attentions=transformer_outputs.attentions,
+        )