Update app.py

app.py

@@ -13,6 +13,12 @@ import gradio as gr
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
+from fastapi.staticfiles import StaticFiles
+app = FastAPI()
+app.mount("/static", StaticFiles(directory="static"), name="static")
+# keep the next line so Gradio UI is still available at /
+app = gr.mount_gradio_app(app, demo, path="/")
+
 MODEL_REPO   = "TheBloke/TinyLlama-1.1B-Chat-GGUF"
 GGUF_FILE    = "tinyllama-1.1b-chat.q4_K_M.gguf"   # 2 GB, 4-bit
 N_CTX        = 4096                                # tokens of context