r

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+# from huggingface_hub import InferenceClient
 from openai import OpenAI
 
 # Modify OpenAI's API key and API base to use vLLM's API server.
@@ -37,7 +37,7 @@ def respond(
     response = ""
 
     for message in client.chat.completions.create(
-        model_name=model_name,
+        model=model_name,
         messages=messages,
         max_tokens=max_tokens,
         stream=True,