Update app.py

app.py

@@ -21,7 +21,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 
 # model = AutoModel.from_pretrained(model_name, trust_remote_code=True).cuda()
 
-# 按需修改，目前只支持 4/8 bit 量化
+# 4/8 bit
 # model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).quantize(4).cuda()
 
 import torch