app.py

app.py

@@ -5,12 +5,13 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 model_name = "AI"  # Replace with the name or path of the model you want to use
 tokenizer = AutoTokenizer.from_pretrained("AI")
 model = AutoModelForSequenceClassification.from_pretrained("AI")
+
 # Values for the new scenario
 new_students = int(input("Enter the number of students in the new scenario: "))
 new_temperature = int(input("Enter the temperature in the new scenario: "))
 
 # Convert the input to tokens
-inputs = tokenizer.encode(
+inputs = tokenizer.encode_plus(
     "Number of students: {}, Temperature: {}".format(new_students, new_temperature),
     padding="max_length",
     truncation=True,
@@ -20,7 +21,7 @@ inputs = tokenizer.encode(
 
 # Make the prediction
 with torch.no_grad():
-    outputs = model(inputs)
+    outputs = model(**inputs)
     logits = outputs.logits
     predicted_rooms = torch.argmax(logits, dim=1).item()