Update app.py

app.py

@@ -1,13 +1,30 @@
+from transformers import AutoModel, AutoTokenizer
 import gradio as gr
-from transformers import AutoTokenizer, AutoModel
+
+#tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+#model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 tokenizer = AutoTokenizer.from_pretrained("silver/chatglm-6b-slim", trust_remote_code=True)
 model = AutoModel.from_pretrained("silver/chatglm-6b-slim", trust_remote_code=True).half().cuda()
 
-def greet(name):
-    response, history = model.chat(tokenizer, "你好", history=[])
-    #return "Hello " + name + "!!"
-    return response
-    
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+model = model.eval()
+
+def predict(input, history=None):
+    if history is None:
+        history = []
+    response, history = model.chat(tokenizer, input, history)
+    return history, history
+
+
+with gr.Blocks() as demo:
+    
+    state = gr.State([])
+    chatbot = gr.Chatbot([], elem_id="chatbot").style(height=400)
+    with gr.Row():
+        with gr.Column(scale=4):
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter").style(container=False)
+        with gr.Column(scale=1):
+            button = gr.Button("Generate")
+    txt.submit(predict, [txt, state], [chatbot, state])
+    button.click(predict, [txt, state], [chatbot, state])
+demo.queue().launch()