Update model use

README.md

@@ -44,6 +44,24 @@ pipeline_tag: text-classification
 ### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```
+from transformers import AutoModelForSequenceClassification
+from transformers import AutoTokenizer
+
+model = AutoModelForSequenceClassification.from_pretrained("AlCyede/sarcastic-text_prediction")
+tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+
+def predict(text):
+    inputs = tokenizer(text, padding=True, truncation=True, return_tensors="pt")
+    outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_id = logits.argmax().item()
+    confidence = logits.softmax(dim=1)[0][predicted_class_id].item()
+    return {
+      "prediction": model.config.id2label[predicted_class_id],
+      "confidence": f"{confidence * 100:.02f}%"
+    }
+```
 
 [More Information Needed]