Update README.md

README.md

@@ -23,4 +23,5 @@ JournaLLM is more than an app; it's a companion on your journey of self-discover
 1. Clone the repository to you local folder: `git clone https://github.com/Ketansuhaas/JournaLLM.git`
 2. Choose a pretrained LLM from [HuggingFace](https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF)
 3. In `app.py`, change the model file in `llm = LlamaCpp(model_path=<model path>, n_ctx=2048)`.
-4. In the terminal, type `streamlit run app.py`.
+4. In the terminal, type `streamlit run app.py`.
+5. To use GPU, set `model_kwargs={"device": "gpu"}`