Update app.py

app.py

@@ -13,9 +13,9 @@ pipe = pipeline("text-generation", model=model_name, device="cpu")
 system_prompt = {"role": "system", "content": "You are an AI assistant. Your task is to generate a detailed and comprehensive response."}
 
 # Define the Gradio interface
-def generate_response(history, user_input, temperature, max_tokens):
+def generate_response(history, user_input, temperature, max_new_tokens):
     messages = [system_prompt] + history + [{"role": "user", "content": user_input}]
-    response = pipe(messages, max_length=max_tokens, temperature=temperature, return_full_text=False)
+    response = pipe(messages, max_new_tokens=max_new_tokens, temperature=temperature, return_full_text=False)
     generated_text = response[0]['generated_text']
     history.append({"role": "user", "content": user_input})
     history.append({"role": "assistant", "content": generated_text})
@@ -44,10 +44,10 @@ with gr.Blocks() as demo:
 
     with gr.Row():
         temperature_slider = gr.Slider(0, 1, 0.7, step=0.1, label="Temperature")
-        max_tokens_slider = gr.Slider(1, 1000, 100, step=1, label="Max Tokens")
+        max_new_tokens_slider = gr.Slider(1, 1000, 100, step=1, label="Max New Tokens")
 
-    send_btn.click(generate_response, [chatbot, txt, temperature_slider, max_tokens_slider], [chatbot, txt])
-    txt.submit(generate_response, [chatbot, txt, temperature_slider, max_tokens_slider], [chatbot, txt])
+    send_btn.click(generate_response, [chatbot, txt, temperature_slider, max_new_tokens_slider], [chatbot, txt])
+    txt.submit(generate_response, [chatbot, txt, temperature_slider, max_new_tokens_slider], [chatbot, txt])
     clear_btn.click(clear_chat, outputs=[chatbot, txt])
 
 # Launch the interface