Update app.py

app.py

@@ -8,7 +8,7 @@ from llama_cpp import Llama
 
 # Set the model repo + filename (change filename if needed)
 MODEL_REPO = "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF"
-MODEL_FILE = "Meta-Llama-3.1-8B-Instruct-abliterated.Q4_K_M.gguf"
+MODEL_FILE = "meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf"
 
 print("Downloading model from HF Hub...")
 model_path = hf_hub_download(
@@ -23,7 +23,7 @@ print(f"Model downloaded to: {model_path}")
 
 llm = Llama(
     model_path=model_path,
-    n_gpu_layers=-1,       # GPU acceleration if available
+    n_gpu_layers=0,       # GPU acceleration if available
     n_ctx=4096,
     chat_format="llama-3",
 )