Add another web demo with Gradio

web_demo3.py

@@ -4,22 +4,23 @@ from typing import TYPE_CHECKING, Any, Callable, Dict, List, Tuple, Type
 import mdtex2html
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).quantize(8).half().cuda()
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 model = model.eval()
 
-# MAX_TURNS = 20
-# MAX_BOXES = MAX_TURNS * 2
-
 """Override Chatbot.postprocess"""
+
+
 def postprocess(self, y):
-        if y is None:
-            return []
-        for i, (message, response) in enumerate(y):
-            y[i] = (
-                None if message is None else mdtex2html.convert((message)),
-                None if response is None else mdtex2html.convert(response),
-            )
-        return y
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
 gr.Chatbot.postprocess = postprocess
 
 
@@ -27,9 +28,10 @@ def predict(input, chatbot, max_length, top_p, temperature, history):
     chatbot.append((input, ""))
     for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
                                                temperature=temperature):
-        chatbot[-1] = (input, response)       
+        chatbot[-1] = (input, response)
         yield chatbot, history
 
+
 def reset_user_input():
     return gr.update(value='')
 
@@ -37,6 +39,7 @@ def reset_user_input():
 def reset_state():
     return [], []
 
+
 with gr.Blocks() as demo:
     gr.HTML("""<h1 align="center">ChatGLM</h1>""")
 
@@ -54,16 +57,17 @@ 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.State([])
 
-    user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True)
+    user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
+                      show_progress=True)
     user_input.submit(reset_user_input, [], [user_input])
 
-    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True)
+    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
+                    show_progress=True)
     submitBtn.click(reset_user_input, [], [user_input])
 
     emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
 
-
-demo.queue().launch(share=False, inbrowser=True)
+demo.queue().launch(share=True, inbrowser=True)