Update app.py

app.py

@@ -12,7 +12,12 @@ if not torch.cuda.is_available():
     DEFAULT_SYSTEM_PROMPT += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
 
 # Create a pipeline using the Hugging Face Llama-2-7b-chat model
-pipe = pipeline("chat", model="huggingface-projects/llama-2-7b-chat", tokenizer="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")
+pipe = pipeline(
+    "chat",
+    model="huggingface-projects/llama-2-7b-chat",
+    tokenizer="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",
+    use_auth_token=True,
+)
 
 # Define a function to interact with the pipeline using Gradio
 def llama_2_7b_chatbot(message):