updated usage

README.md

@@ -10,6 +10,14 @@ Based on Hugging Face's albert-base-v2, albertZero employs a novel method to spe
 
 albertZero can be loaded like this:
 
+```python
+tokenizer = AutoTokenizer.from_pretrained('MarshallHo/albertZero-squad2-base-v2')
+model = AutoModel.from_pretrained('MarshallHo/albertZero-squad2-base-v2')
+
+```
+
+or 
+
 ```python
 from transformers import AlbertModel, AlbertTokenizer, AlbertForQuestionAnswering, AlbertPreTrainedModel
 
@@ -19,7 +27,6 @@ model.load_state_dict(torch.load('albertZero-squad2-base-v2.bin'))
 ```
 
 
-
 ## References
 
 The goal of [ALBERT](https://arxiv.org/abs/1909.11942) is to reduce the memory requirement of the groundbreaking