Update app.py

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 import json
 model_path = 'THUDM/chatglm-6b'
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
-model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().float()
+model = AutoModel.from_pretrained(model_path, trust_remote_code=True).bfloat16()
 model = model.eval()
 
 MAX_TURNS = 20
@@ -34,9 +34,9 @@ with gr.Blocks() as demo:
     text_boxes = []
     for i in range(MAX_BOXES):
         if i % 2 == 0:
-            text_boxes.append(gr.Text(visible=False, label="提问："))
+            text_boxes.append(gr.Markdown(visible=False, label="提问："))
         else:
-            text_boxes.append(gr.Text(visible=False, label="回复："))
+            text_boxes.append(gr.Markdown(visible=False, label="回复："))
 
     with gr.Row():
         with gr.Column(scale=4):
@@ -46,7 +46,6 @@ with gr.Blocks() as demo:
             max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
             top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
             temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
-            history = gr.TextArea(visible=False)
             button = gr.Button("Generate")
-    button.click(predict, [txt, max_length, top_p, temperature, history, state], [state] + text_boxes, queue=True)
-demo.queue(concurrency_count=10).launch(enable_queue=True, max_threads=2)
+    button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes)
+demo.queue().launch(share=True, inbrowser=True)