Update app.py

app.py

@@ -94,9 +94,7 @@ llm = ChatLlamaCpp(
     temperature=0,
     model_path="./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf",
     n_ctx=10000,
-    n_gpu_layers=8,
     n_batch=300,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
-    max_tokens=512,
     n_threads=multiprocessing.cpu_count() - 1,
     repeat_penalty=1.5,
     top_p=0.5,