feat: use inference endpoint

app.py

@@ -1,11 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+
+token = os.environ.get("HF_TOKEN")
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient(
-    model="Orenguteng/Llama-3-8B-Lexi-Uncensored")
+    model="https://mw6ztcar07ths6bp.us-east-1.aws.endpoints.huggingface.cloud",
+    token=token
+)
 
 
 def respond(