Update app.py

app.py

@@ -13,7 +13,7 @@ model = AutoModelForCausalLM.from_pretrained(
     model_file=MODEL_FILE,
     model_type="mistral",
     # gpu_layers=50 if torch.cuda.is_available() else 0,  # Use GPU if available
-    context_length=1024  # Reduce context length for faster response
+    context_length=256  # Reduce context length for faster response
 )
 print("Model loaded successfully.")