github
/
ChatGLM2-6B
mirror of https://github.com/THUDM/ChatGLM2-6B
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update web_demo.py 

使用更先进的方式加载模型
pull/129/head
zxgov 2023-06-30 10:26:50 +08:00 committed by GitHub
parent e84a5f3c14
commit 07d463034b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
web_demo.py
View File

@ -4,7 +4,7 @@ import mdtex2html
from utils import load_model_on_gpus from utils import load_model_on_gpus
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) 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 # 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 # from utils import load_model_on_gpus
# model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2) # model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)