Update app.py

app.py

@@ -1,6 +1,6 @@
 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()
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().quantize(4).cuda()
 response, history = model.chat(tokenizer, "你好", history=[])
 print(response)
 response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)