fix python 2.7 imports

README.md

@@ -45,6 +45,12 @@ PyTorch pretrained bert can be installed by pip as follows:
 pip install pytorch-pretrained-bert
 ```
 
+If you want to use the tokenizer associated to the `OpenAI GPT` tokenizer, you will need to install `ftfy` (if you are using Python 2, version 4.4.3 is the last version working for you) and `SpaCy` :
+```bash
+pip install spacy ftfy==4.4.3
+python -m spacy download en
+```
+
 ### From source
 
 Clone the repository and run:
@@ -52,6 +58,13 @@ Clone the repository and run:
 pip install [--editable] .
 ```
 
+Here also, if you want to use `OpenAIGPT` tokenizer, you will need to install `ftfy` (limit to version 4.4.3 if you are using Python 2) and `SpaCy` :
+```bash
+pip install spacy ftfy==4.4.3
+python -m spacy download en
+```
+
+
 A series of tests is included in the [tests folder](https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/tests) and can be run using `pytest` (install pytest if needed: `pip install pytest`).
 
 You can run the tests with the command:

pytorch_pretrained_bert/file_utils.py

@@ -29,7 +29,7 @@ try:
     from pathlib import Path
     PYTORCH_PRETRAINED_BERT_CACHE = Path(os.getenv('PYTORCH_PRETRAINED_BERT_CACHE',
                                                    Path.home() / '.pytorch_pretrained_bert'))
-except ImportError:
+except AttributeError:
     PYTORCH_PRETRAINED_BERT_CACHE = os.getenv('PYTORCH_PRETRAINED_BERT_CACHE',
                                               os.path.join(os.path.expanduser("~"), '.pytorch_pretrained_bert'))
 

tests/tokenization_openai_test.py

@@ -32,7 +32,7 @@ class OpenAIGPTTokenizationTest(unittest.TestCase):
                  "low</w>", "lowest</w>", "newer</w>", "wider</w>"]
         vocab_tokens = dict(zip(vocab, range(len(vocab))))
         merges = ["#version: 0.2", "l o", "lo w", "e r</w>", ""]
-        with open("/tmp/openai_tokenizer_vocab_test.json", "w", encoding='utf-8') as fp:
+        with open("/tmp/openai_tokenizer_vocab_test.json", "wb") as fp:
             json.dump(vocab_tokens, fp)
             vocab_file = fp.name
         with open("/tmp/openai_tokenizer_merges_test.txt", "w", encoding='utf-8') as fp: