remove huggingface client

app.py

@@ -3,8 +3,6 @@ from threading import Thread
 import gradio as gr
 import re
 import torch
-from huggingface_hub import InferenceClient
-
 
 # load model and tokenizer
 model_name = "inclusionAI/Ling-mini-2.0"
@@ -22,13 +20,12 @@ def respond(
     system_message,
     max_tokens,
     temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
+    top_p
 ):
     """
     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(token=hf_token.token, model="openai/gpt-oss-20b")
+    #client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
     messages = [{"role": "system", "content": system_message}]