From e84a5f3c14eca59672fb38e7eceb686e1e0ea5d6 Mon Sep 17 00:00:00 2001
From: zxgov <64576649+zx2021@users.noreply.github.com>
Date: Fri, 30 Jun 2023 10:26:12 +0800
Subject: [PATCH] Update cli_demo.py
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

使用更先进的方式加载模型
---
 cli_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cli_demo.py b/cli_demo.py
index 4aa35d3..586218e 100644
--- a/cli_demo.py
+++ b/cli_demo.py
@@ -5,7 +5,7 @@ from transformers import AutoTokenizer, AutoModel
 import readline
 
 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，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
 # from utils import load_model_on_gpus
 # model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)