Update app.py

app.py

@@ -1,6 +1,15 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+AVAILABLE_MODELS = [
+    "openai/gpt-oss-20b",
+    "openai/gpt-oss-mini-20b",
+    "meta-llama/Llama-3.3-70B-Instruct",
+    "meta-llama/Llama-3.1-8B-Instruct",
+    "mistralai/Mistral-7B-Instruct-v0.3",
+    "Qwen/Qwen2.5-72B-Instruct",
+    "microsoft/Phi-3.5-mini-instruct",
+]
 
 def respond(
     message,
@@ -9,17 +18,13 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    model_name,
     hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+    client = InferenceClient(token=hf_token.token, model=model_name)
 
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
@@ -40,9 +45,6 @@ def respond(
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -56,14 +58,22 @@ chatbot = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Dropdown(
+            choices=AVAILABLE_MODELS,
+            value=AVAILABLE_MODELS[0],
+            label="🤖 Model",
+            info="Chọn model để chat",
+        ),
     ],
 )
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
+        gr.Markdown("### ⚙️ Cài đặt")
+        gr.Markdown("Đăng nhập để sử dụng các model HuggingFace.")
     chatbot.render()
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()