Update app.py

app.py

@@ -1,8 +1,8 @@
 from lmdeploy.serve.gradio.turbomind_coupled import *
 from lmdeploy.messages import TurbomindEngineConfig
 
-backend_config = TurbomindEngineConfig(max_batch_size=1, cache_max_entry_count=0.05, model_format='awq')
-model_path = 'internlm/internlm2-chat-20b-4bits'
+backend_config = TurbomindEngineConfig(max_batch_size=1, cache_max_entry_count=0.05)#, model_format='awq')
+model_path = 'internlm/internlm2-math-7b'
 
 InterFace.async_engine = AsyncEngine(
     model_path=model_path,
@@ -80,13 +80,13 @@ with gr.Blocks(css=CSS, theme=THEME) as demo:
         with gr.Row():
             request_output_len = gr.Slider(1,
                                             2048,
-                                            value=512,
+                                            value=1024,
                                             step=1,
                                             label='Maximum new tokens')
-            top_p = gr.Slider(0.01, 1, value=0.8, step=0.01, label='Top_p')
+            top_p = gr.Slider(0.01, 1, value=1.0, step=0.01, label='Top_p')
             temperature = gr.Slider(0.01,
                                     1.5,
-                                    value=0.7,
+                                    value=0.01,
                                     step=0.01,
                                     label='Temperature')