Fix Code Example in README

README.md

@@ -30,14 +30,15 @@ The table connects the position of the predicted probability to its dimension.
 # Usage Example
 
 ```python
-from transformers import AutoModel
+import torch
+from transformers import AutoModelForSequenceClassification
 from transformers import AutoTokenizer
 
 # load tokenizer
 tokenizer = AutoTokenizer.from_pretrained("luerhard/PopBERT")
 
 # load model
-model = AutoModel.from_pretrained("luerhard/PopBERT")
+model = AutoModelForSequenceClassification.from_pretrained("luerhard/PopBERT")
 
 # define text to be predicted
 text = (
@@ -47,7 +48,7 @@ text = (
 )
 
 # encode text with tokenizer
-encodings = tokenizer(text)
+encodings = tokenizer(text, return_tensors="pt")
 
 # predict
 with torch.inference_mode():
@@ -59,7 +60,7 @@ print(probs.detach().numpy())
 ```
 
 ```
-array([[0.87651485, 0.34838045, 0.983123  , 0.02148381]], dtype=float32)
+[[0.8765146  0.34838045 0.983123   0.02148379]]
 ```
 
 
@@ -71,7 +72,7 @@ To maximize performance, it is recommended to use the following thresholds per d
 [0.415961, 0.295400, 0.429109, 0.302714]
 ```
 
-Using these thresholds, the model achieves the follwing performance on the test set:
+Using these thresholds, the model achieves the following performance on the test set:
 
 | Dimension           | Precision     | Recall        | F1            |
 |---------------------|---------------|---------------|---------------|