Update app.py

app.py

@@ -25,7 +25,7 @@ if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 if  torch.cuda.is_available():
-    modelA_id = "meta-llama/Llama-2-7b-chat-hf"
+    modelA_id = "meta-llama/Llama-2-7b-hf"
     bnb_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_use_double_quant=False,
@@ -106,7 +106,7 @@ logging.basicConfig(level=logging.DEBUG)
 # Gradio Interface Setup
 chat_interface = gr.ChatInterface(
     fn=generate,
-    additional_inputs=[gr.Dropdown("Model", ["A", "B"],label="Animal", info="Will add more animals later!")],
+    additional_inputs=[gr.Dropdown(["A", "B"],label="Model", info="Will add more animals later!")],
     fill_height=True,
     stop_btn=None,
     examples=[