diff --git a/examples/run_classifier.py b/examples/run_classifier.py
index fb78b6efeb7..d79c2526b07 100644
--- a/examples/run_classifier.py
+++ b/examples/run_classifier.py
@@ -857,7 +857,6 @@ def main():
                     optimizer.zero_grad()
                     global_step += 1
 
-    if args.do_train:
         # Save a trained model and the associated configuration
         model_to_save = model.module if hasattr(model, 'module') else model  # Only save the model it-self
         output_model_file = os.path.join(args.output_dir, WEIGHTS_NAME)
diff --git a/examples/run_squad.py b/examples/run_squad.py
index a29362ffb97..bb335ce75c9 100644
--- a/examples/run_squad.py
+++ b/examples/run_squad.py
@@ -471,7 +471,7 @@ def write_predictions(all_examples, all_features, all_results, n_best_size,
         prelim_predictions = []
         # keep track of the minimum score of null start+end of position 0
         score_null = 1000000  # large and positive
-        min_null_feature_index = 0  # the paragraph slice with min mull score
+        min_null_feature_index = 0  # the paragraph slice with min null score
         null_start_logit = 0  # the start logit at the slice with min null score
         null_end_logit = 0  # the end logit at the slice with min null score
         for (feature_index, feature) in enumerate(features):
@@ -620,7 +620,7 @@ def write_predictions(all_examples, all_features, all_results, n_best_size,
                 all_predictions[example.qas_id] = ""
             else:
                 all_predictions[example.qas_id] = best_non_null_entry.text
-                all_nbest_json[example.qas_id] = nbest_json
+            all_nbest_json[example.qas_id] = nbest_json
 
     with open(output_prediction_file, "w") as writer:
         writer.write(json.dumps(all_predictions, indent=4) + "\n")
@@ -657,8 +657,8 @@ def get_final_text(pred_text, orig_text, do_lower_case, verbose_logging=False):
     #
     # What we really want to return is "Steve Smith".
     #
-    # Therefore, we have to apply a semi-complicated alignment heruistic between
-    # `pred_text` and `orig_text` to get a character-to-charcter alignment. This
+    # Therefore, we have to apply a semi-complicated alignment heuristic between
+    # `pred_text` and `orig_text` to get a character-to-character alignment. This
     # can fail in certain cases in which case we just return `orig_text`.
 
     def _strip_spaces(text):
diff --git a/examples/run_swag.py b/examples/run_swag.py
index 2ebd637223c..ab8e147cae9 100644
--- a/examples/run_swag.py
+++ b/examples/run_swag.py
@@ -15,6 +15,8 @@
 # limitations under the License.
 """BERT finetuning runner."""
 
+from __future__ import absolute_import
+
 import argparse
 import csv
 import logging
@@ -31,7 +33,7 @@ from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
 from pytorch_pretrained_bert.file_utils import PYTORCH_PRETRAINED_BERT_CACHE
-from pytorch_pretrained_bert.modeling import BertForMultipleChoice
+from pytorch_pretrained_bert.modeling import (BertForMultipleChoice, BertConfig, WEIGHTS_NAME, CONFIG_NAME)
 from pytorch_pretrained_bert.optimization import BertAdam, warmup_linear
 from pytorch_pretrained_bert.tokenization import BertTokenizer
 
diff --git a/pytorch_pretrained_bert/modeling_gpt2.py b/pytorch_pretrained_bert/modeling_gpt2.py
index 69bd088a4e7..c381b288f86 100644
--- a/pytorch_pretrained_bert/modeling_gpt2.py
+++ b/pytorch_pretrained_bert/modeling_gpt2.py
@@ -15,6 +15,8 @@
 # limitations under the License.
 """PyTorch OpenAI GPT-2 model."""
 
+from __future__ import absolute_import, division, print_function, unicode_literals
+
 import collections
 import copy
 import json
diff --git a/pytorch_pretrained_bert/modeling_openai.py b/pytorch_pretrained_bert/modeling_openai.py
index d73ee66f50c..296abbfc314 100644
--- a/pytorch_pretrained_bert/modeling_openai.py
+++ b/pytorch_pretrained_bert/modeling_openai.py
@@ -15,6 +15,8 @@
 # limitations under the License.
 """PyTorch OpenAI GPT model."""
 
+from __future__ import absolute_import, division, print_function, unicode_literals
+
 import collections
 import copy
 import json
diff --git a/pytorch_pretrained_bert/modeling_transfo_xl.py b/pytorch_pretrained_bert/modeling_transfo_xl.py
index b225316f3d8..ac895a03a7e 100644
--- a/pytorch_pretrained_bert/modeling_transfo_xl.py
+++ b/pytorch_pretrained_bert/modeling_transfo_xl.py
@@ -18,6 +18,8 @@
     In particular https://github.com/kimiyoung/transformer-xl/blob/master/pytorch/mem_transformer.py
 """
 
+from __future__ import absolute_import, division, print_function, unicode_literals
+
 import os
 import copy
 import json