Update app.py

app.py

@@ -62,7 +62,7 @@ def load_model():
                                                 embedding=True,
                                                 verbose=False,
                                                 n_ctx=1024,
-                                                n_threads = 4,
+                                                n_threads = 2,
                                                 n_gpu_layers=0,     # The number of layers to offload to GPU, if you have GPU acceleration available
                                                 chat_format="llama-2",
                                                 cache_dir='./model_cached'