Update README.md

README.md

@@ -46,7 +46,7 @@ f1 = 82.50
 exact match = 70.49
 ```
 
-## How to use the model
+## How to use the model... with Pipeline
 
 ```python
 import transformers
@@ -77,6 +77,27 @@ print(f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start:
 # Answer: '1 de dezembro de 2019', score: 0.713, start: 328, end: 349
 ```
 
+## How to use the model... with the Auto classes
+
+```python
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+  
+tokenizer = AutoTokenizer.from_pretrained("pierreguillou/bert-base-cased-squad-v1.1-portuguese")
+model = AutoModelForQuestionAnswering.from_pretrained("pierreguillou/bert-base-cased-squad-v1.1-portuguese")
+```             
+
+Or just clone the model repo:
+
+```python
+git lfs install
+git clone https://huggingface.co/pierreguillou/bert-base-cased-squad-v1.1-portuguese
+  
+# if you want to clone without large files – just their pointers
+# prepend your git clone with the following env var:
+  
+GIT_LFS_SKIP_SMUDGE=1
+```               
+
 ## Limitations and bias
 
 The training data used for this model come from Portuguese SQUAD. It could contain a lot of unfiltered content, which is far from neutral, and biases.