Update app.py

app.py

@@ -2,13 +2,9 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from optillm.moa import mixture_of_agents 
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
 def respond(
+    model,
+    approach,
     message,
     history: list[tuple[str, str]],
     system_message,
@@ -16,6 +12,7 @@ def respond(
     temperature,
     top_p,
 ):
+    client = InferenceClient(model)
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -48,10 +45,10 @@ demo = gr.ChatInterface(
     additional_inputs=[
         gr.Dropdown(
             ["meta-llama/Meta-Llama-3.1-70B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct", "HuggingFaceH4/zephyr-7b-beta"], label="Model", info="Choose the base model"
-        )
+        ),
         gr.Dropdown(
             ["bon", "mcts", "moa"], label="Approach", info="Choose the approach"
-        )
+        ),
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),