app.py

app.py

@@ -2,21 +2,16 @@ import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 # Load the model and tokenizer
-model_name = "your_model_name"  # Replace with the name of the model you want to use
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-
+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 new number of students: "))  # Number of students in the new scenario
-new_temperature = int(input("Enter new temperature: "))  # Temperature in the new scenario
-
-# Create the feature array for the new scenario
-new_scenario = [1, new_students, new_temperature]
+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_plus(
+inputs = tokenizer.encode(
     "Number of students: {}, Temperature: {}".format(new_students, new_temperature),
-    add_special_tokens=True,
     padding="max_length",
     truncation=True,
     max_length=64,
@@ -25,11 +20,11 @@ inputs = tokenizer.encode_plus(
 
 # Make the prediction
 with torch.no_grad():
-    outputs = model(**inputs)
+    outputs = model(inputs)
     logits = outputs.logits
-    predicted_rooms = torch.argmax(logits).item()
+    predicted_rooms = torch.argmax(logits, dim=1).item()
 
 # Print the results
 print("Number of students:", new_students)
 print("Temperature:", new_temperature)
-print("Predicted number of rooms:", predicted_rooms)
+print("Predicted label for number of rooms:", predicted_rooms)