Update app.py

app.py

@@ -7,7 +7,7 @@ def respond(
     history: list[dict[str, str]],
     hf_token: gr.OAuthToken,
 ):
-    client = InferenceClient(token=hf_token.token, model="Qwen/Qwen3-8B")
+    client = InferenceClient(token=hf_token.token, model="Qwen/Qwen3-8B", provider="featherless-ai")
 
     messages = []
 
@@ -24,6 +24,7 @@ def respond(
         choices = message.choices
         token = ""
         if len(choices) and choices[0].delta.content:
+            print("choices", choices)
             token = choices[0].delta.content
             print("token", token)