Update README.md

README.md

@@ -24,6 +24,30 @@ It achieves the following results on the evaluation set:
 - Loss: 0.3812
 - Accuracy: 0.9083
 
+# Load model directly
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("execbat/bert-finetuned-sst2")
+model = AutoModelForSequenceClassification.from_pretrained("execbat/bert-finetuned-sst2")
+```
+
+## Use a pipeline as a high-level helper
+```python
+from transformers import pipeline
+
+label_tags = {'LABEL_0' : "NEGATIVE",
+             'LABEL_1' : "POSITIVE"}
+
+pipe = pipeline("text-classification", model="execbat/bert-finetuned-sst2")
+result = pipe(["what a horrible day!", "what a wonderfull day!"])
+encoded_result = [label_tags[i["label"]] for i in result]
+print(encoded_result)
+```
+```python
+['NEGATIVE', 'POSITIVE']
+```
+
 ## Model description
 
 More information needed