Update app.py

app.py

@@ -0,0 +1,53 @@
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch.nn.functional as F
+
+def load_model(model_directory):
+    # Assuming 'config.json' and 'pytorch_model.bin' are in 'model_directory'
+    model = AutoModelForSequenceClassification.from_pretrained(model_directory)
+    tokenizer = AutoTokenizer.from_pretrained(model_directory)
+    return model, tokenizer
+
+def predict(model, tokenizer, input_text):
+    # Preprocess the input
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
+    
+    # Move tensors to the same device as the model
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+
+    # Model in evaluation mode
+    model.eval()
+    
+    # Make the model generate a prediction
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+
+    # Convert logits to probabilities
+    probabilities = F.softmax(logits, dim=1)
+
+    # Get the predicted class and the probabilities
+    predicted_class = torch.argmax(probabilities, dim=1).cpu().numpy()
+    probabilities = probabilities.cpu().numpy()
+
+    return predicted_class, probabilities
+
+def main():
+    # Replace 'your-model-directory' with the actual path to your model directory
+    model_directory = "Kurkur99/modeling"  # e.g., "Kurkur99/Kurkur99/transactionmerchant/model_directory"
+    model, tokenizer = load_model(model_directory)
+
+    # Example input text
+    input_text = "Example input text for prediction"
+    
+    # Get predictions
+    predicted_class, probabilities = predict(model, tokenizer, input_text)
+    
+    # Output the results
+    print(f"Predicted Class: {predicted_class[0]}")
+    print(f"Probabilities: {probabilities[0]}")
+
+if __name__ == "__main__":
+    main()