Update app.py

app.py

@@ -6,7 +6,7 @@ token = os.getenv("TOKEN")
 endpoint = os.getenv("ENDPOINT")
 
 # initialize InferenceClient
-client = InferenceClient(model=endpoint, token=token)
+client = InferenceClient(model="https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf", token=token)
 
 # query client using streaming mode
 def inference(message, history):