Add HAT implementation files

modelling_hat.py

@@ -1093,6 +1093,26 @@ class HATForMaskedLM(HATPreTrainedModel):
     def set_output_embeddings(self, new_embeddings):
         self.lm_head.decoder = new_embeddings
 
+    def _tie_or_clone_weights(self, output_embeddings, input_embeddings):
+        """Tie or clone module weights depending of whether we are using TorchScript or not"""
+        if self.config.torchscript:
+            output_embeddings.weight = nn.Parameter(input_embeddings.weight.clone())
+        else:
+            output_embeddings.weight = input_embeddings.weight
+
+        if getattr(output_embeddings, "bias", None) is not None:
+            output_embeddings.bias.data = nn.functional.pad(
+                output_embeddings.bias.data,
+                (
+                    0,
+                    output_embeddings.weight.shape[0] - output_embeddings.bias.shape[0],
+                ),
+                "constant",
+                0,
+            )
+        if hasattr(output_embeddings, "out_features") and hasattr(input_embeddings, "num_embeddings"):
+            output_embeddings.out_features = input_embeddings.num_embeddings
+
     @add_start_docstrings_to_model_forward(HAT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,