Expose get_config() on ModelTesters (#12812)

* Expose get_config() on ModelTesters

* Typo

tests/test_modeling_gpt2.py

@@ -17,7 +17,7 @@
 import datetime
 import unittest
 
-from transformers import is_torch_available
+from transformers import GPT2Config, is_torch_available
 from transformers.testing_utils import require_torch, slow, torch_device
 
 from .test_configuration_common import ConfigTester
@@ -30,7 +30,6 @@ if is_torch_available():
 
     from transformers import (
         GPT2_PRETRAINED_MODEL_ARCHIVE_LIST,
-        GPT2Config,
         GPT2DoubleHeadsModel,
         GPT2ForSequenceClassification,
         GPT2LMHeadModel,
@@ -119,25 +118,7 @@ class GPT2ModelTester:
             token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
             choice_labels = ids_tensor([self.batch_size], self.num_choices)
 
-        config = GPT2Config(
-            vocab_size=self.vocab_size,
-            n_embd=self.hidden_size,
-            n_layer=self.num_hidden_layers,
-            n_head=self.num_attention_heads,
-            # intermediate_size=self.intermediate_size,
-            # hidden_act=self.hidden_act,
-            # hidden_dropout_prob=self.hidden_dropout_prob,
-            # attention_probs_dropout_prob=self.attention_probs_dropout_prob,
-            n_positions=self.max_position_embeddings,
-            n_ctx=self.max_position_embeddings,
-            # type_vocab_size=self.type_vocab_size,
-            # initializer_range=self.initializer_range,
-            use_cache=not gradient_checkpointing,
-            bos_token_id=self.bos_token_id,
-            eos_token_id=self.eos_token_id,
-            pad_token_id=self.pad_token_id,
-            gradient_checkpointing=gradient_checkpointing,
-        )
+        config = self.get_config(gradient_checkpointing=gradient_checkpointing)
 
         head_mask = ids_tensor([self.num_hidden_layers, self.num_attention_heads], 2)
 
@@ -153,6 +134,27 @@ class GPT2ModelTester:
             choice_labels,
         )
 
+    def get_config(self, gradient_checkpointing=False):
+        return GPT2Config(
+            vocab_size=self.vocab_size,
+            n_embd=self.hidden_size,
+            n_layer=self.num_hidden_layers,
+            n_head=self.num_attention_heads,
+            intermediate_size=self.intermediate_size,
+            hidden_act=self.hidden_act,
+            hidden_dropout_prob=self.hidden_dropout_prob,
+            attention_probs_dropout_prob=self.attention_probs_dropout_prob,
+            n_positions=self.max_position_embeddings,
+            n_ctx=self.max_position_embeddings,
+            type_vocab_size=self.type_vocab_size,
+            initializer_range=self.initializer_range,
+            use_cache=not gradient_checkpointing,
+            bos_token_id=self.bos_token_id,
+            eos_token_id=self.eos_token_id,
+            pad_token_id=self.pad_token_id,
+            gradient_checkpointing=gradient_checkpointing,
+        )
+
     def prepare_config_and_inputs_for_decoder(self):
         (
             config,