update

architectures/codeparrot.txt

@@ -5,7 +5,7 @@
 | GPT2 | 110M |
 | GPT2 | 1.5B |
 
-You can load the model and tokenizer directly from the `transformers`:
+You can load the model and tokenizer directly from `transformers`:
 
 ```python
 from transformers import AutoTokenizer, AutoModelWithLMHead
@@ -18,7 +18,7 @@ outputs = model(**inputs)
 
 ```
 
-Or you can use a pipeline
+Or you can use a `pipeline`:
 
 ```python
 from transformers import pipeline