Update README.md

README.md

@@ -57,14 +57,20 @@ model = AutoModelForSequenceClassification.from_pretrained(
     "UMCU/ICD10_classifier_base_English",
     trust_remote_code=True,
 )
-```
+tokenizer = AutoTokenizer.from_pretrained("UMCU/ICD10_classifier_base_English")
+model.eval()
 
-or 
+inputs = tokenizer(
+    text,
+    return_tensors="pt",
+    truncation=True,
+)
 
-```python
-from transformers import pipeline
+with torch.no_grad():
+    features = model(**inputs).logits
 
-le_pipe = pipeline('text-classification',trust_remote_code=True, model="UMCU/ICD10_classifier_base_English")
 ```
 
+
+
 The macro f1 score is 0.73. We suggest to use it primarily for feature extraction or for use as an *explainable* embedder.