Upload app.py with huggingface_hub

app.py

@@ -4,7 +4,6 @@ import threading
 import spaces
 import gradio as gr
 from huggingface_hub import hf_hub_download
-from llama_cpp import Llama
 
 logging.basicConfig(level=logging.INFO)
 log = logging.getLogger(__name__)
@@ -37,9 +36,10 @@ threading.Thread(target=download_model, daemon=True).start()
 def generate(messages, max_tokens=1024, temperature=0.7, top_p=0.95):
     global _llm
     if _llm is None:
+        from llama_cpp import Llama as _Llama
         _downloaded.wait()
         log.info("Loading model into GPU...")
-        _llm = Llama(
+        _llm = _Llama(
             model_path=MODEL_PATH,
             n_gpu_layers=-1,
             n_ctx=8192,