Add 0 gpu layers

app.py

@@ -41,7 +41,7 @@ model_path = hf_hub_download(
 
 print(f"Loading model from {model_path}...")
 from llama_cpp import Llama
-llm = Llama(model_path=model_path, n_gpu_layers=-1, n_ctx=2048)
+llm = Llama(model_path=model_path, n_gpu_layers=0, n_ctx=2048)
 
 # --- 3. TTS Setup (Coqui) ---
 print("Loading TTS...")