Update app.py

app.py

@@ -32,7 +32,7 @@ model, tokenizer = load_model_and_tokenizer()
 
 # Generate Response
 # =================
-def generate_response(prompt, chat_history):
+def generate_response(prompt, chat_history, max_new_tokens, temperature):
     """
     Generate a response from the model based on the user prompt and chat history.
     """
@@ -46,11 +46,11 @@ def generate_response(prompt, chat_history):
 
     generated_ids = model.generate(
         **model_inputs,
-        max_new_tokens=512,
+        max_new_tokens=max_new_tokens,
         do_sample=True,
         top_k=50,
         top_p=0.95,
-        temperature=0.7,
+        temperature=temperature,
         output_scores=True,
         return_dict_in_generate=True,
         return_legacy_cache=True  # Ensure legacy format is returned
@@ -76,19 +76,28 @@ def gradio_interface():
     Create and launch the Gradio interface.
     """
     with gr.Blocks() as demo:
-        chatbot = gr.Chatbot(label="Chat with Qwen/Qwen2.5-Coder-0.5B-Instruct", type="messages")
-        msg = gr.Textbox(label="User Input")
-        clear = gr.Button("Clear Chat")
+        with gr.Row():
+            with gr.Column(scale=3):
+                chatbot = gr.Chatbot(label="Chat with Qwen/Qwen2.5-Coder-0.5B-Instruct", type="messages")
+                msg = gr.Textbox(label="User Input")
+                with gr.Row():
+                    submit = gr.Button("Submit")
+                    clear = gr.Button("Clear Chat")
+            with gr.Column(scale=1):
+                with gr.Box():
+                    gr.Markdown("### Settings")
+                    max_new_tokens = gr.Slider(50, 1024, value=512, step=1, label="Max New Tokens")
+                    temperature = gr.Slider(0.1, 1.0, value=0.7, step=0.05, label="Temperature")
 
-        def respond(message, chat_history):
+        def respond(message, chat_history, max_new_tokens, temperature):
             chat_history.append({"role": "user", "content": message})
             response = ""
-            for chunk in generate_response(message, chat_history):
+            for chunk in generate_response(message, chat_history, max_new_tokens, temperature):
                 response = chunk
                 yield chat_history + [{"role": "assistant", "content": response}]
             chat_history.append({"role": "assistant", "content": response})
 
-        msg.submit(respond, [msg, chatbot], [chatbot])
+        submit.click(respond, [msg, chatbot, max_new_tokens, temperature], [chatbot])
         clear.click(clear_chat, None, [chatbot])
 
     demo.launch()