Update README.md

README.md

@@ -9,7 +9,7 @@ This is a [roberta](https://arxiv.org/pdf/1907.11692.pdf) pre-trained version on
 
 To load the model:
 (necessary packages: !pip install transformers sentencepiece)
-```php
+```python
 from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
 tokenizer = AutoTokenizer.from_pretrained("dbernsohn/roberta-php")
 model = AutoModelWithLMHead.from_pretrained("dbernsohn/roberta-php")
@@ -23,7 +23,7 @@ fill_mask = pipeline(
 
 You can then use this model to fill masked words in a Java code.
 
-```php
+```python
 code = """
 $people = array(
     array('name' => 'Kalle', 'salt' => 856412),