Update app.py

app.py

@@ -16,8 +16,8 @@ adapter_path = hf_hub_download(repo_id=adapter_repo, filename=adapter_file)
 llm = Llama(
     model_path=base_model_path,
     lora_path=adapter_path,
-    n_ctx=1024,       # Context length, set manually since adapter lacks it
-    n_threads=4,     # Adjust based on your system
+    n_ctx=512,       # Context length, set manually since adapter lacks it
+    n_threads=2,     # Adjust based on your system
     n_gpu_layers=0    # Set to >0 if GPU acceleration is desired and supported
 )