docs: fix readme

README.md

@@ -73,6 +73,7 @@ for sentX in sentenceL:
   inputList.append(sentence)
 tokenized_text = tokenizer(inputList, padding = True, return_tensors = 'pt')
 token_ids = tokenized_text['input_ids']
+
 with torch.no_grad():
     features = model(**tokenized_text, output_hidden_states = True).hidden_states[-1]
 ```
@@ -81,7 +82,7 @@ To use HoogBERTa as an embedding layer, use
 
 ```python
 with torch.no_grad():
-  features = model(token_ids) # where token_ids is a tensor with type "long".
+  features = model(token_ids, output_hidden_states = True).hidden_states[-1] # where token_ids is a tensor with type "long".
 ```