main.py updated

main.py

@@ -37,7 +37,7 @@ n_batch = 512  # Should be between 1 and n_ctx, consider the amount of VRAM in y
 
 # Make sure the model path is correct for your system!
 llm = LlamaCpp(
-    model_path="Meta-Llama-3-8B-Instruct-v2.Q4_K_S.gguf",
+    model_path="Phi-3-mini-4k-instruct-q4.gguf",
     n_gpu_layers=n_gpu_layers,
     n_batch=n_batch,
     callback_manager=callback_manager,