Update api.py

使用更先进的方式加载模型

api.py

@@ -51,7 +51,7 @@ async def create_item(request: Request):
 
 if __name__ == '__main__':
     tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
+    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')#.cuda()
     # 多显卡支持，使用下面三行代替上面两行，将num_gpus改为你实际的显卡数量
     # model_path = "THUDM/chatglm2-6b"
     # tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)