Update app.py

app.py

@@ -95,6 +95,7 @@ def inference(prompt, hf_token, model, model_name):
     messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": prompt}]
     if hf_token is None or not hf_token.strip():
         hf_token = os.getenv("HF_TOKEN")
+        print("using hf token env")
     client = InferenceClient(model=model, token=hf_token)
     tokens = f"**`{model_name}`**\n\n"
     for completion in client.chat_completion(messages, max_tokens=200, stream=True):