Update README.md

README.md

@@ -18,10 +18,10 @@ This adapter was created for usage with the **[Adapters](https://github.com/Adap
 
 ## Usage
 
-First, install `adapters`:
+First, install `transformers` and `adapters`:
 
 ```
-pip install -U adapters
+pip install -U transformers adapters
 ```
 
 Now, the adapter can be loaded and activated like this:
@@ -36,6 +36,8 @@ adapter_name
 Next, to perform sentiment classification:
 
 ```python
+from transformers import AutoTokenizer, TextClassificationPipeline
+
 tokenizer = AutoTokenizer.from_pretrained("roberta-base")
 classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
 classfifier("Adapters are awesome!")