More logging + timeout if model is not loaded + url not needed

app.py

@@ -1,12 +1,15 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from huggingface_hub import logging
 import os 
 
+logging.set_verbosity_info()
+
 token = os.getenv("TOKEN")
 endpoint = os.getenv("ENDPOINT")
 
 # initialize InferenceClient
-client = InferenceClient(model="https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf", token=token)
+client = InferenceClient(model="meta-llama/Llama-2-7b-chat-hf", timeout=60, token=token)
 
 # query client using streaming mode
 def inference(message, history):