Update app.py

app.py

@@ -9,7 +9,7 @@ from llama_cpp_agent.providers import LlamaCppPythonProvider
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 # client = InferenceClient("cognitivecomputations/dolphin-2.8-mistral-7b-v02")
-llama_model = Llama(r"Meta-Llama-3-8B.Q5_K_M.gguf", n_batch=1024, n_threads=10, n_gpu_layers=33, n_ctx=8192, verbose=False)
+llama_model = Llama(r"Meta-Llama-3-8B.Q5_K_M.gguf", n_batch=1024, n_threads=4, n_gpu_layers=33, n_ctx=8192, verbose=False)
 
 provider = LlamaCppPythonProvider(llama_model)