add model option dropdown

app.py

@@ -16,6 +16,7 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    model,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -31,7 +32,7 @@ def respond(
 
     for message in client.chat_completion(
         messages,
-        model="meta-llama/Meta-Llama-3.1-8B-Instruct",
+        model=model  #"meta-llama/Meta-Llama-3.1-8B-Instruct",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
@@ -46,19 +47,27 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
+
+# List of model IDs
+model_options = [
+    "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    "meta-llama/Meta-Llama-3.1-70B-Instruct",
+    "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8",
+    "meta-llama/Meta-Llama-3-8B-Instruct",
+    "meta-llama/Meta-Llama-3-70B-Instruct",
+    "mistralai/Mistral-7B-Instruct-v0.3",
+    "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "mistralai/Mixtral-8x22B-Instruct-v0.1",
+]
+
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         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"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.Dropdown(choices=model_options, value=model_options[0], label="Model"),  # Dropdown for model selection
     ],
 )