Update app.py

app.py

@@ -28,7 +28,7 @@ def predict_sql_injection(query, hf_token):
     inference_model = FastLanguageModel.for_inference(model)
     
     prompt = f"### Instruction:\nClassify the following SQL query as normal (0) or an injection attack (1).\n\n### Query:\n{query}\n\n### Classification:\n"
-    inputs = tokenizer(prompt, return_tensors="pt").to("cpu")
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 
     # Use the inference model for generation
     outputs = inference_model.generate(